immit dictionary is an MCP server published by co.immit, hosted at api.immit.co. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 6 tools, including lookup_word, search_words, conjugate, annotate_passage, report_missing_word.
The immit English and Japanese dictionary: entries, search and inflection tables for an agent
1 connections through 4 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
The immit dictionary entry for one English or Japanese word: its senses with definitions, translations and example sentence pairs, every inflected form as a row with its reading, the pronunciations with IPA for English or the kana reading and pitch accent for Japanese and a playable MP3 URL for each, the frequency rank, synonyms and antonyms, and alternative spellings. Call it rather than answering from memory whenever the question is about pitch accent, a reading, an inflection table, how a word sounds, an example sentence, how common a word is, or an exact definition: those are the facts a model guesses wrong. text is the word as it is written: the dictionary form, a case variant, an alternative spelling or an inflected form (食べた answers 食べる, went answers go) resolves to its entry, whose headword is the dictionary form. A form that is also a headword answers that entry (saw is the tool, not see), and a form two entries inflect to answers the more common one; search_words lists every entry a form matches. The result is the entry JSON that the immit://entry-shape resource describes field by field.
| Parameter | Type | Description |
|---|---|---|
| lang * | string | The language of the word: eng for English, jpn for Japanese |
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
| text * | string | The word as written: its dictionary form, an alternative spelling or an inflected form; matched exactly, then case-folded |
{
"name": "lookup_word",
"title": "Look up a word",
"description": "The immit dictionary entry for one English or Japanese word: its senses with definitions, translations and example sentence pairs, every inflected form as a row with its reading, the pronunciations with IPA for English or the kana reading and pitch accent for Japanese and a playable MP3 URL for each, the frequency rank, synonyms and antonyms, and alternative spellings. Call it rather than answering from memory whenever the question is about pitch accent, a reading, an inflection table, how a word sounds, an example sentence, how common a word is, or an exact definition: those are the facts a model guesses wrong. text is the word as it is written: the dictionary form, a case variant, an alternative spelling or an inflected form (食べた answers 食べる, went answers go) resolves to its entry, whose headword is the dictionary form. A form that is also a headword answers that entry (saw is the tool, not see), and a form two entries inflect to answers the more common one; search_words lists every entry a form matches. The result is the entry JSON that the immit://entry-shape resource describes field by field.",
"inputSchema": {
"type": "object",
"required": [
"lang",
"text"
],
"properties": {
"lang": {
"enum": [
"eng",
"jpn"
],
"type": "string",
"description": "The language of the word: eng for English, jpn for Japanese"
},
"text": {
"type": "string",
"description": "The word as written: its dictionary form, an alternative spelling or an inflected form; matched exactly, then case-folded"
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"title": "DictionaryEntry",
"required": [
"id",
"headword",
"lang",
"frequency_rank",
"updated_at",
"inflections",
"senses",
"pronunciations"
],
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"lang": {
"enum": [
"eng",
"jpn"
],
"type": "string"
},
"senses": {
"type": "array",
"items": {
"type": "object",
"title": "DictionarySense",
"required": [
"id",
"pos",
"definition",
"translations",
"examples",
"homograph",
"pos_translations"
],
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"pos": {
"type": "string",
"description": "Part of speech in the entry's language: verb, 動詞"
},
"examples": {
"type": "array",
"items": {
"type": "object",
"title": "DictionaryExample",
"required": [
"id",
"sentences"
],
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"sentences": {
"type": "array",
"items": {
"type": "object",
"title": "DictionaryExampleSentence",
"required": [
"id",
"lang",
"text"
],
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"lang": {
"enum": [
"eng",
"jpn"
],
"type": "string"
},
"text": {
"type": "string"
}
}
}
}
}
},
"description": "Parallel sentence pairs, one sentence per language"
},
"homograph": {
"type": "integer",
"format": "int32",
"description": "Which homograph of the headword the sense belongs to"
},
"definition": {
"type": "string",
"description": "In the entry's own language"
},
"translations": {
"type": "object",
"title": "DictionaryTranslations",
"description": "One key per language the sense is translated into: 'eng' on a Japanese entry, 'jpn' on an English one",
"additionalProperties": {
"type": "object",
"required": [
"glosses",
"qualifier"
],
"properties": {
"glosses": {
"type": "array",
"items": {
"type": "object",
"required": [
"id",
"text"
],
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"text": {
"type": "string"
},
"readings": {
"type": "array",
"items": {
"type": "string"
},
"description": "Kana readings of a Japanese gloss; empty when unknown"
}
}
}
},
"qualifier": {
"type": [
"object",
"null"
],
"required": [
"id",
"text"
],
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"text": {
"type": "string"
}
},
"description": "A domain or register, such as 野球 on a baseball sense"
}
}
}
},
"pos_translations": {
"type": "object",
"properties": {
"eng": {
"type": [
"string",
"null"
]
},
"jpn": {
"type": [
"string",
"null"
]
}
}
}
}
}
},
"headword": {
"type": "string",
"description": "The canonical headword. A case variant, a spelling or an inflected form in the request resolves to it"
},
"relations": {
"type": "array",
"items": {
"type": "object",
"title": "DictionaryRelation",
"required": [
"sense_id",
"homograph",
"pos",
"kind",
"headword",
"entry_id"
],
"properties": {
"pos": {
"type": "string"
},
"kind": {
"type": "string",
"description": "synonym or antonym; more kinds can follow"
},
"entry_id": {
"type": "string",
"format": "uuid"
},
"headword": {
"type": "string"
},
"sense_id": {
"type": "string",
"format": "uuid"
},
"homograph": {
"type": "integer",
"format": "int32"
}
},
"description": "A related word of one sense: another entry of the same language. homograph and pos are the sense's"
},
"description": "Always served. Not required, because a device parses entries stored before the field existed"
},
"spellings": {
"type": "array",
"items": {
"type": "object",
"title": "DictionarySpelling",
"required": [
"homograph",
"text",
"label",
"label_translations",
"inflection_texts"
],
"properties": {
"text": {
"type": "string",
"description": "Another written form of the same word: 喰べる for 食べる"
},
"label": {
"type": "string",
"description": "What the spelling is beside the headword, in the entry's language"
},
"homograph": {
"type": "integer",
"format": "int32"
},
"inflection_texts": {
"type": "array",
"items": {
"type": "string"
},
"description": "The texts that inflect this spelling: lookup surfaces with no form"
},
"label_translations": {
"type": "object",
"properties": {
"eng": {
"type": [
"string",
"null"
]
},
"jpn": {
"type": [
"string",
"null"
]
}
}
}
},
"description": "Another written form of the homograph: the same word, pronunciation and senses, written another way"
},
"description": "Always served. Not required, because a device parses entries stored before the field existed"
},
"updated_at": {
"type": "string",
"format": "date-time",
"description": "When the entry last changed. A recomputed frequency_rank and a renamed part of speech, spelling label or inflection form do not move it; the ETag moves with every change"
},
"inflections": {
"type": "array",
"items": {
"type": "object",
"title": "DictionaryInflection",
"required": [
"id",
"form",
"text",
"homograph",
"polarity",
"tone",
"pos",
"form_translations",
"form_sequence",
"pronunciations"
],
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"pos": {
"type": "string"
},
"form": {
"type": "string",
"description": "The form name in the entry's language: て形, past tense"
},
"text": {
"type": "string",
"description": "The surface form: 食べて, walked"
},
"tone": {
"enum": [
"plain",
"polite",
null
],
"type": [
"string",
"null"
],
"description": "Japanese only; null on English rows"
},
"polarity": {
"enum": [
"positive",
"negative",
null
],
"type": [
"string",
"null"
],
"description": "Set on Japanese forms and on a few English negative forms; null elsewhere"
},
"homograph": {
"type": "integer",
"format": "int32"
},
"form_sequence": {
"type": "integer",
"format": "int32",
"description": "Display order of the form within the entry's table"
},
"pronunciations": {
"type": "array",
"items": {
"type": "object",
"title": "DictionaryInflectionPronunciation",
"required": [
"id",
"ipa",
"reading",
"dialect",
"accent",
"sounds"
],
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"ipa": {
"type": [
"string",
"null"
],
"description": "IPA on English rows; null on Japanese rows"
},
"accent": {
"type": [
"integer",
"null"
],
"format": "int32",
"description": "Pitch accent, Japanese only: the mora after which the pitch drops, 0 for heiban"
},
"sounds": {
"type": "array",
"items": {
"type": "object",
"title": "DictionaryInflectionSound",
"required": [
"id",
"key",
"mp3_url",
"voice",
"gender",
"alphabet"
],
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"key": {
"type": "string",
"description": "The storage key behind the URL"
},
"voice": {
"type": "string",
"description": "Himari, Emma or Michael"
},
"gender": {
"enum": [
"male",
"female"
],
"type": "string"
},
"mp3_url": {
"type": "string",
"description": "Playable as is, and cacheable"
},
"alphabet": {
"enum": [
"ipa",
"phonetic"
],
"type": "string"
}
}
}
},
"dialect": {
"type": [
"string",
"null"
],
"description": "AmE on English rows; null on Japanese rows"
},
"reading": {
"type": [
"string",
"null"
],
"description": "Kana reading on Japanese rows; null on English rows"
}
}
},
"description": "The reading of this form; usually empty on English rows"
},
"form_translations": {
"type": "object",
"properties": {
"eng": {
"type": [
"string",
"null"
]
},
"jpn": {
"type": [
"string",
"null"
]
}
}
}
}
},
"description": "Every form as a row, so a client never deinflects"
},
"frequency_rank": {
"type": [
"integer",
"null"
],
"format": "int32",
"description": "1 is the most frequent entry of its language; null when unranked"
},
"pronunciations": {
"type": "array",
"items": {
"type": "object",
"title": "DictionaryPronunciation",
"required": [
"id",
"homograph",
"ipa",
"reading",
"dialect",
"accent",
"sounds"
],
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"ipa": {
"type": [
"string",
"null"
],
"description": "IPA on English rows; null on Japanese rows"
},
"accent": {
"type": [
"integer",
"null"
],
"format": "int32",
"description": "Pitch accent, Japanese only: the mora after which the pitch drops, 0 for heiban"
},
"sounds": {
"type": "array",
"items": {
"type": "object",
"title": "DictionarySound",
"required": [
"id",
"key",
"mp3_url",
"voice",
"gender",
"alphabet"
],
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"key": {
"type": "string",
"description": "The storage key behind the URL"
},
"voice": {
"type": "string",
"description": "Himari, Emma or Michael"
},
"gender": {
"enum": [
"male",
"female"
],
"type": "string"
},
"mp3_url": {
"type": "string",
"description": "Playable as is, and cacheable"
},
"alphabet": {
"enum": [
"ipa",
"phonetic"
],
"type": "string"
}
}
}
},
"dialect": {
"type": [
"string",
"null"
],
"description": "AmE on English rows; null on Japanese rows"
},
"reading": {
"type": [
"string",
"null"
],
"description": "Kana reading on Japanese rows; null on English rows"
},
"homograph": {
"type": "integer",
"format": "int32"
}
}
}
}
}
}
}The immit dictionary entries that match a string: a headword prefix, an alternative spelling, an inflected form (食べた finds 食べる, walked finds walk) or, for Japanese, a reading in kana or in romaji (たべる and taberu find 食べる). Results are ranked: an exact headword or spelling first, then an exact inflected form or reading, then a Japanese reading that romaji spells without its long vowels (tokyo finds 東京), then the prefix matches, each rank by frequency with the most common first. Each result is a whole entry, as lookup_word returns it. A query that matches nothing comes back with suggestions, the nearest queries that do match an entry (orangw suggests orange); search again with one of them. Use it to turn a reading or a fragment into the headword, to see every entry a form belongs to, or to list the words that start with a string; use lookup_word when you hold the word itself, in whatever form.
| Parameter | Type | Description |
|---|---|---|
| lang * | string | The language of the word: eng for English, jpn for Japanese |
| limit | integer | Entries to return, 10 unless given, capped at 25; each is a whole entry, so ask for few |
| query * | string | A headword prefix, a spelling, an inflected form or a reading in kana or romaji, whatever the case |
{
"name": "search_words",
"title": "Search words",
"description": "The immit dictionary entries that match a string: a headword prefix, an alternative spelling, an inflected form (食べた finds 食べる, walked finds walk) or, for Japanese, a reading in kana or in romaji (たべる and taberu find 食べる). Results are ranked: an exact headword or spelling first, then an exact inflected form or reading, then a Japanese reading that romaji spells without its long vowels (tokyo finds 東京), then the prefix matches, each rank by frequency with the most common first. Each result is a whole entry, as lookup_word returns it. A query that matches nothing comes back with suggestions, the nearest queries that do match an entry (orangw suggests orange); search again with one of them. Use it to turn a reading or a fragment into the headword, to see every entry a form belongs to, or to list the words that start with a string; use lookup_word when you hold the word itself, in whatever form.",
"inputSchema": {
"type": "object",
"required": [
"lang",
"query"
],
"properties": {
"lang": {
"enum": [
"eng",
"jpn"
],
"type": "string",
"description": "The language of the word: eng for English, jpn for Japanese"
},
"limit": {
"type": "integer",
"default": 10,
"maximum": 25,
"minimum": 1,
"description": "Entries to return, 10 unless given, capped at 25; each is a whole entry, so ask for few"
},
"query": {
"type": "string",
"description": "A headword prefix, a spelling, an inflected form or a reading in kana or romaji, whatever the case"
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"title": "DictionaryEntriesPage",
"required": [
"entries",
"suggestions",
"metadata"
],
"properties": {
"entries": {
"type": "array",
"items": {
"type": "object",
"title": "DictionaryEntry",
"required": [
"id",
"headword",
"lang",
"frequency_rank",
"updated_at",
"inflections",
"senses",
"pronunciations"
],
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"lang": {
"enum": [
"eng",
"jpn"
],
"type": "string"
},
"senses": {
"type": "array",
"items": {
"type": "object",
"title": "DictionarySense",
"required": [
"id",
"pos",
"definition",
"translations",
"examples",
"homograph",
"pos_translations"
],
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"pos": {
"type": "string",
"description": "Part of speech in the entry's language: verb, 動詞"
},
"examples": {
"type": "array",
"items": {
"type": "object",
"title": "DictionaryExample",
"required": [
"id",
"sentences"
],
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"sentences": {
"type": "array",
"items": {
"type": "object",
"title": "DictionaryExampleSentence",
"required": [
"id",
"lang",
"text"
],
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"lang": {
"enum": [
"eng",
"jpn"
],
"type": "string"
},
"text": {
"type": "string"
}
}
}
}
}
},
"description": "Parallel sentence pairs, one sentence per language"
},
"homograph": {
"type": "integer",
"format": "int32",
"description": "Which homograph of the headword the sense belongs to"
},
"definition": {
"type": "string",
"description": "In the entry's own language"
},
"translations": {
"type": "object",
"title": "DictionaryTranslations",
"description": "One key per language the sense is translated into: 'eng' on a Japanese entry, 'jpn' on an English one",
"additionalProperties": {
"type": "object",
"required": [
"glosses",
"qualifier"
],
"properties": {
"glosses": {
"type": "array",
"items": {
"type": "object",
"required": [
"id",
"text"
],
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"text": {
"type": "string"
},
"readings": {
"type": "array",
"items": {
"type": "string"
},
"description": "Kana readings of a Japanese gloss; empty when unknown"
}
}
}
},
"qualifier": {
"type": [
"object",
"null"
],
"required": [
"id",
"text"
],
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"text": {
"type": "string"
}
},
"description": "A domain or register, such as 野球 on a baseball sense"
}
}
}
},
"pos_translations": {
"type": "object",
"properties": {
"eng": {
"type": [
"string",
"null"
]
},
"jpn": {
"type": [
"string",
"null"
]
}
}
}
}
}
},
"headword": {
"type": "string",
"description": "The canonical headword. A case variant, a spelling or an inflected form in the request resolves to it"
},
"relations": {
"type": "array",
"items": {
"type": "object",
"title": "DictionaryRelation",
"required": [
"sense_id",
"homograph",
"pos",
"kind",
"headword",
"entry_id"
],
"properties": {
"pos": {
"type": "string"
},
"kind": {
"type": "string",
"description": "synonym or antonym; more kinds can follow"
},
"entry_id": {
"type": "string",
"format": "uuid"
},
"headword": {
"type": "string"
},
"sense_id": {
"type": "string",
"format": "uuid"
},
"homograph": {
"type": "integer",
"format": "int32"
}
},
"description": "A related word of one sense: another entry of the same language. homograph and pos are the sense's"
},
"description": "Always served. Not required, because a device parses entries stored before the field existed"
},
"spellings": {
"type": "array",
"items": {
"type": "object",
"title": "DictionarySpelling",
"required": [
"homograph",
"text",
"label",
"label_translations",
"inflection_texts"
],
"properties": {
"text": {
"type": "string",
"description": "Another written form of the same word: 喰べる for 食べる"
},
"label": {
"type": "string",
"description": "What the spelling is beside the headword, in the entry's language"
},
"homograph": {
"type": "integer",
"format": "int32"
},
"inflection_texts": {
"type": "array",
"items": {
"type": "string"
},
"description": "The texts that inflect this spelling: lookup surfaces with no form"
},
"label_translations": {
"type": "object",
"properties": {
"eng": {
"type": [
"string",
"null"
]
},
"jpn": {
"type": [
"string",
"null"
]
}
}
}
},
"description": "Another written form of the homograph: the same word, pronunciation and senses, written another way"
},
"description": "Always served. Not required, because a device parses entries stored before the field existed"
},
"updated_at": {
"type": "string",
"format": "date-time",
"description": "When the entry last changed. A recomputed frequency_rank and a renamed part of speech, spelling label or inflection form do not move it; the ETag moves with every change"
},
"inflections": {
"type": "array",
"items": {
"type": "object",
"title": "DictionaryInflection",
"required": [
"id",
"form",
"text",
"homograph",
"polarity",
"tone",
"pos",
"form_translations",
"form_sequence",
"pronunciations"
],
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"pos": {
"type": "string"
},
"form": {
"type": "string",
"description": "The form name in the entry's language: て形, past tense"
},
"text": {
"type": "string",
"description": "The surface form: 食べて, walked"
},
"tone": {
"enum": [
"plain",
"polite",
null
],
"type": [
"string",
"null"
],
"description": "Japanese only; null on English rows"
},
"polarity": {
"enum": [
"positive",
"negative",
null
],
"type": [
"string",
"null"
],
"description": "Set on Japanese forms and on a few English negative forms; null elsewhere"
},
"homograph": {
"type": "integer",
"format": "int32"
},
"form_sequence": {
"type": "integer",
"format": "int32",
"description": "Display order of the form within the entry's table"
},
"pronunciations": {
"type": "array",
"items": {
"type": "object",
"title": "DictionaryInflectionPronunciation",
"required": [
"id",
"ipa",
"reading",
"dialect",
"accent",
"sounds"
],
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"ipa": {
"type": [
"string",
"null"
],
"description": "IPA on English rows; null on Japanese rows"
},
"accent": {
"type": [
"integer",
"null"
],
"format": "int32",
"description": "Pitch accent, Japanese only: the mora after which the pitch drops, 0 for heiban"
},
"sounds": {
"type": "array",
"items": {
"type": "object",
"title": "DictionaryInflectionSound",
"required": [
"id",
"key",
"mp3_url",
"voice",
"gender",
"alphabet"
],
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"key": {
"type": "string",
"description": "The storage key behind the URL"
},
"voice": {
"type": "string",
"description": "Himari, Emma or Michael"
},
"gender": {
"enum": [
"male",
"female"
],
"type": "string"
},
"mp3_url": {
"type": "string",
"description": "Playable as is, and cacheable"
},
"alphabet": {
"enum": [
"ipa",
"phonetic"
],
"type": "string"
}
}
}
},
"dialect": {
"type": [
"string",
"null"
],
"description": "AmE on English rows; null on Japanese rows"
},
"reading": {
"type": [
"string",
"null"
],
"description": "Kana reading on Japanese rows; null on English rows"
}
}
},
"description": "The reading of this form; usually empty on English rows"
},
"form_translations": {
"type": "object",
"properties": {
"eng": {
"type": [
"string",
"null"
]
},
"jpn": {
"type": [
"string",
"null"
]
}
}
}
}
},
"description": "Every form as a row, so a client never deinflects"
},
"frequency_rank": {
"type": [
"integer",
"null"
],
"format": "int32",
"description": "1 is the most frequent entry of its language; null when unranked"
},
"pronunciations": {
"type": "array",
"items": {
"type": "object",
"title": "DictionaryPronunciation",
"required": [
"id",
"homograph",
"ipa",
"reading",
"dialect",
"accent",
"sounds"
],
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"ipa": {
"type": [
"string",
"null"
],
"description": "IPA on English rows; null on Japanese rows"
},
"accent": {
"type": [
"integer",
"null"
],
"format": "int32",
"description": "Pitch accent, Japanese only: the mora after which the pitch drops, 0 for heiban"
},
"sounds": {
"type": "array",
"items": {
"type": "object",
"title": "DictionarySound",
"required": [
"id",
"key",
"mp3_url",
"voice",
"gender",
"alphabet"
],
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"key": {
"type": "string",
"description": "The storage key behind the URL"
},
"voice": {
"type": "string",
"description": "Himari, Emma or Michael"
},
"gender": {
"enum": [
"male",
"female"
],
"type": "string"
},
"mp3_url": {
"type": "string",
"description": "Playable as is, and cacheable"
},
"alphabet": {
"enum": [
"ipa",
"phonetic"
],
"type": "string"
}
}
}
},
"dialect": {
"type": [
"string",
"null"
],
"description": "AmE on English rows; null on Japanese rows"
},
"reading": {
"type": [
"string",
"null"
],
"description": "Kana reading on Japanese rows; null on English rows"
},
"homograph": {
"type": "integer",
"format": "int32"
}
}
}
}
}
}
},
"metadata": {
"type": "object",
"required": [
"after",
"before",
"limit"
],
"properties": {
"after": {
"type": [
"string",
"null"
],
"description": "Cursor for the next page; null on the last"
},
"limit": {
"type": "integer",
"format": "int32",
"description": "The page size that was applied"
},
"before": {
"type": [
"string",
"null"
],
"description": "Cursor for the previous page; null on the first"
}
}
},
"suggestions": {
"type": "array",
"items": {
"type": "string"
},
"description": "For a query that matched no entry, up to three queries near it that do, the nearest first: orangw suggests orange, にがた suggests にいがた and yomiu suggests yomu. A Japanese query in kana is answered in kana and one in romaji in romaji. Empty when the page has an entry and when nothing is near."
}
}
}
}The inflection table of one English or Japanese word, grouped by form in the order a textbook table shows them: for Japanese the polite, て, past, negative and other forms, for English the third person, past, participle or plural. Each form carries its name in the word's language with English and Japanese translations, and one row per surface with the text, the polarity (positive or negative) and tone (plain or polite) on Japanese rows, the homograph it belongs to, the part of speech and the kana reading. The pitch accent and the MP3 are the headword's, on the pronunciations lookup_word answers, not each row's. Call it to say how a word is conjugated or inflected, the polite past of 帰る for example, rather than inflecting it yourself. headword resolves as lookup_word's text does. A word with no inflections, a Japanese noun or a particle, answers an empty forms list, not an error.
| Parameter | Type | Description |
|---|---|---|
| lang * | string | The language of the word: eng for English, jpn for Japanese |
| headword * | string | The word as written: its dictionary form, an alternative spelling or an inflected form |
{
"name": "conjugate",
"title": "Conjugate a word",
"description": "The inflection table of one English or Japanese word, grouped by form in the order a textbook table shows them: for Japanese the polite, て, past, negative and other forms, for English the third person, past, participle or plural. Each form carries its name in the word's language with English and Japanese translations, and one row per surface with the text, the polarity (positive or negative) and tone (plain or polite) on Japanese rows, the homograph it belongs to, the part of speech and the kana reading. The pitch accent and the MP3 are the headword's, on the pronunciations lookup_word answers, not each row's. Call it to say how a word is conjugated or inflected, the polite past of 帰る for example, rather than inflecting it yourself. headword resolves as lookup_word's text does. A word with no inflections, a Japanese noun or a particle, answers an empty forms list, not an error.",
"inputSchema": {
"type": "object",
"required": [
"lang",
"headword"
],
"properties": {
"lang": {
"enum": [
"eng",
"jpn"
],
"type": "string",
"description": "The language of the word: eng for English, jpn for Japanese"
},
"headword": {
"type": "string",
"description": "The word as written: its dictionary form, an alternative spelling or an inflected form"
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"title": "DictionaryConjugation",
"required": [
"id",
"headword",
"lang",
"forms"
],
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"lang": {
"enum": [
"eng",
"jpn"
],
"type": "string"
},
"forms": {
"type": "array",
"items": {
"type": "object",
"required": [
"form",
"form_translations",
"form_sequence",
"rows"
],
"properties": {
"form": {
"type": "string",
"description": "The form name in the entry's language: て形, past tense"
},
"rows": {
"type": "array",
"items": {
"type": "object",
"required": [
"text",
"homograph",
"polarity",
"tone",
"pos",
"pronunciations"
],
"properties": {
"pos": {
"type": "string"
},
"text": {
"type": "string",
"description": "The surface form: 食べて, walked"
},
"tone": {
"enum": [
"plain",
"polite",
null
],
"type": [
"string",
"null"
],
"description": "Japanese only; null on English rows"
},
"polarity": {
"enum": [
"positive",
"negative",
null
],
"type": [
"string",
"null"
],
"description": "Set on Japanese forms and on a few English negative forms; null elsewhere"
},
"homograph": {
"type": "integer",
"format": "int32"
},
"pronunciations": {
"type": "array",
"items": {
"type": "object",
"title": "DictionaryInflectionPronunciation",
"required": [
"id",
"ipa",
"reading",
"dialect",
"accent",
"sounds"
],
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"ipa": {
"type": [
"string",
"null"
],
"description": "IPA on English rows; null on Japanese rows"
},
"accent": {
"type": [
"integer",
"null"
],
"format": "int32",
"description": "Pitch accent, Japanese only: the mora after which the pitch drops, 0 for heiban"
},
"sounds": {
"type": "array",
"items": {
"type": "object",
"title": "DictionaryInflectionSound",
"required": [
"id",
"key",
"mp3_url",
"voice",
"gender",
"alphabet"
],
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"key": {
"type": "string",
"description": "The storage key behind the URL"
},
"voice": {
"type": "string",
"description": "Himari, Emma or Michael"
},
"gender": {
"enum": [
"male",
"female"
],
"type": "string"
},
"mp3_url": {
"type": "string",
"description": "Playable as is, and cacheable"
},
"alphabet": {
"enum": [
"ipa",
"phonetic"
],
"type": "string"
}
}
}
},
"dialect": {
"type": [
"string",
"null"
],
"description": "AmE on English rows; null on Japanese rows"
},
"reading": {
"type": [
"string",
"null"
],
"description": "Kana reading on Japanese rows; null on English rows"
}
}
},
"description": "The reading of this form; usually empty on English rows"
}
}
},
"description": "The surfaces of the form, one per homograph, polarity and tone, the positive and plain ones first"
},
"form_sequence": {
"type": "integer",
"format": "int32",
"description": "Display order of the form within the entry's table"
},
"form_translations": {
"type": "object",
"properties": {
"eng": {
"type": [
"string",
"null"
]
},
"jpn": {
"type": [
"string",
"null"
]
}
}
}
}
},
"description": "One group per form in form_sequence order; empty for an entry with no inflection rows, such as a noun or a particle"
},
"headword": {
"type": "string",
"description": "The canonical headword the lookup resolved to"
}
},
"description": "The entry's inflection rows grouped by form in the order the entry's table shows them"
}
}Every word of a Japanese or English passage as a row, in one call: the word as the passage writes it and where it sits, its language, its base form (the headword lookup_word takes), the kana reading chosen with the other readings the written form has, the inflected form it is written in with polarity and tone, the headword's pitch accent, how common the word is in five bands, its word class and the entry's first gloss. Call it before you say, teach or correct a sentence, rather than splitting it into words and looking each one up: a word is the longest run the dictionary holds as one written form, so 見に行きました is one row with its form named. The reading is the one chosen for the word, not a promise for a homograph: when it matters, read other_readings. The gloss is the entry's first, not the sense the passage uses; lookup_word has every sense. A word with no entry, a name for example, is a row with a null headword. passage is at most 500 characters: send a longer passage a few sentences at a time.
| Parameter | Type | Description |
|---|---|---|
| passage * | string | The text as written, Japanese, English or both, at most 500 characters |
{
"name": "annotate_passage",
"title": "Annotate a passage",
"description": "Every word of a Japanese or English passage as a row, in one call: the word as the passage writes it and where it sits, its language, its base form (the headword lookup_word takes), the kana reading chosen with the other readings the written form has, the inflected form it is written in with polarity and tone, the headword's pitch accent, how common the word is in five bands, its word class and the entry's first gloss. Call it before you say, teach or correct a sentence, rather than splitting it into words and looking each one up: a word is the longest run the dictionary holds as one written form, so 見に行きました is one row with its form named. The reading is the one chosen for the word, not a promise for a homograph: when it matters, read other_readings. The gloss is the entry's first, not the sense the passage uses; lookup_word has every sense. A word with no entry, a name for example, is a row with a null headword. passage is at most 500 characters: send a longer passage a few sentences at a time.",
"inputSchema": {
"type": "object",
"required": [
"passage"
],
"properties": {
"passage": {
"type": "string",
"maxLength": 500,
"description": "The text as written, Japanese, English or both, at most 500 characters"
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"title": "PassageAnnotation",
"required": [
"characters",
"rows"
],
"properties": {
"rows": {
"type": "array",
"items": {
"type": "object",
"title": "PassageRow",
"required": [
"surface",
"start",
"end",
"lang",
"headword",
"reading",
"other_readings",
"form",
"accent",
"frequency_band",
"pos",
"gloss"
],
"properties": {
"end": {
"type": "integer",
"format": "int32",
"description": "Where the surface ends, exclusive"
},
"pos": {
"type": [
"string",
"null"
],
"description": "The word class, named in the word's language"
},
"form": {
"description": "The inflected form the word is written in; null for a word in its base form"
},
"lang": {
"enum": [
"eng",
"jpn"
],
"type": "string"
},
"gloss": {
"type": [
"string",
"null"
],
"description": "The entry's first gloss under the reading chosen, in the other language: not the sense the passage uses"
},
"start": {
"type": "integer",
"format": "int32",
"description": "Where the surface starts in the passage, in Unicode code points from 0"
},
"accent": {
"type": [
"integer",
"null"
],
"format": "int32",
"description": "jpn only. The headword's pitch accent, the mora after which the pitch falls and 0 for none; an inflected form carries its headword's. Null where the entry has none"
},
"reading": {
"type": [
"string",
"null"
],
"description": "jpn only. The reading chosen for the surface, in kana. A written form can have several readings, and `other_readings` lists the rest"
},
"surface": {
"type": "string",
"description": "The word as the passage writes it: the longest run the dictionary holds as one written form, so 見に行きました is one row"
},
"headword": {
"type": [
"string",
"null"
],
"description": "The base form: the headword of the word's entry, which the entry route answers in full. Null for a word with no entry, a name for example, which has a reading and nothing else below"
},
"frequency_band": {
"enum": [
"very_common",
"common",
"uncommon",
"rare",
"very_rare",
null
],
"type": [
"string",
"null"
],
"description": "How common the entry is in its language, in five bands. Null for a word with no entry and for an entry the dictionary has not ranked"
},
"other_readings": {
"type": "array",
"items": {
"type": "string"
},
"description": "jpn only. Every other reading the written form has"
}
}
},
"description": "A row for each word, in the order the passage writes them. Punctuation and symbols have no row"
},
"characters": {
"type": "integer",
"format": "int32",
"description": "The characters the passage has, each drawn from the balance"
}
}
}
}Tell immit that a real word has no entry, so a lexicographer adds one. Call it when lookup_word and search_words both miss a word a person asked about and you are confident the word exists in that language: a headword in its dictionary form, never an inflected form, a typo or a proper noun. context is optional, the sentence the word came from or what the person wanted to know. The report is read by a person; nothing is added on the spot, so answer the person from what you know and say the dictionary lacks the word.
| Parameter | Type | Description |
|---|---|---|
| lang * | string | The language of the word: eng for English, jpn for Japanese |
| text * | string | The missing word in its dictionary form |
| context | string | Where the word came up, or what the person asked |
{
"name": "report_missing_word",
"title": "Report a missing word",
"description": "Tell immit that a real word has no entry, so a lexicographer adds one. Call it when lookup_word and search_words both miss a word a person asked about and you are confident the word exists in that language: a headword in its dictionary form, never an inflected form, a typo or a proper noun. context is optional, the sentence the word came from or what the person wanted to know. The report is read by a person; nothing is added on the spot, so answer the person from what you know and say the dictionary lacks the word.",
"inputSchema": {
"type": "object",
"required": [
"lang",
"text"
],
"properties": {
"lang": {
"enum": [
"eng",
"jpn"
],
"type": "string",
"description": "The language of the word: eng for English, jpn for Japanese"
},
"text": {
"type": "string",
"maxLength": 100,
"description": "The missing word in its dictionary form"
},
"context": {
"type": "string",
"maxLength": 2000,
"description": "Where the word came up, or what the person asked"
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"received"
],
"properties": {
"received": {
"type": "boolean",
"const": true
}
},
"additionalProperties": false
}
}Send the people who make immit a note: an entry that looks wrong, a tool that answered badly, a field you wished an entry had. A person reads it. For a word with no entry use report_missing_word instead. Name the word and the language when the note is about one entry.
| Parameter | Type | Description |
|---|---|---|
| lang | string | The language of the word: eng for English, jpn for Japanese |
| text | string | The headword the note is about, when it is about one |
| message * | string | The note, in plain words |
{
"name": "send_feedback",
"title": "Send feedback",
"description": "Send the people who make immit a note: an entry that looks wrong, a tool that answered badly, a field you wished an entry had. A person reads it. For a word with no entry use report_missing_word instead. Name the word and the language when the note is about one entry.",
"inputSchema": {
"type": "object",
"required": [
"message"
],
"properties": {
"lang": {
"enum": [
"eng",
"jpn"
],
"type": "string",
"description": "The language of the word: eng for English, jpn for Japanese"
},
"text": {
"type": "string",
"maxLength": 100,
"description": "The headword the note is about, when it is about one"
},
"message": {
"type": "string",
"maxLength": 2000,
"description": "The note, in plain words"
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"received"
],
"properties": {
"received": {
"type": "boolean",
"const": true
}
},
"additionalProperties": false
}
}immit is a dictionary for learners of Japanese and English. Its entries carry what a model guesses wrong: pitch accent, readings, the whole inflection table, example sentence pairs, audio and frequency. Look a word up before answering about any of those, and annotate a passage before saying or teaching it. The immit://entry-shape resource describes every field of an entry. Calling a tool takes an immit developer key as the bearer header, made in a minute at https://immit.co/developers/console; a call without one is refused.
Names, descriptions and schemas were written by the server and are shown as data.