Agent Reliability
Testing, benchmarking and auditing autonomous AI agents — methods, harnesses, evidence
사용해야 할까요
품질 및 안전성
A
도구 정의와 프로토콜 준수에 대한 자동 분석을 기반으로 합니다.
컨텍스트 비용
~6,459토큰 (도구 정의)
~7.4 KB일반적인 응답 크기
상당한 주의 영향 (128k 컨텍스트의 5.05%)
이는 서버의 도구가 모델의 컨텍스트에 로드될 때마다 소비되는 대략적인 토큰 수입니다. 수치가 높을수록 다른 작업에 사용할 수 있는 주의가 줄어듭니다.
설치
원클릭 설치
`claude_desktop_config.json` 파일에 다음을 추가하세요:
{
"mcpServers": {
"agent-reliability": {
"url": "https://agentreliability.dev/mcp?via=manifest"
}
}
}원격 엔드포인트
https://agentreliability.dev/mcp?via=manifeststreamable-http할 수 있는 일
도구 목록
도구 (9)
🟢 읽기 전용🟡 쓰기🔴 삭제⚪ 알 수 없음
🟢search(query, limit)
Full-text search over the knowledge graph. Matching ignores accents and apostrophes, so query in the user's own words; every hit carries the fields it matched and a score. BM25 relevance: each query term is weighted by how RARE it is in this corpus and by where it hits (name 3, tags 2, questions 2, body 1). A hit must also cover a minimum share of the question's information, measured in the same rarity weights — matching only common words does not qualify. Centrality (how many objects point at this one) breaks TIES ONLY and is never part of the score, so it cannot make an irrelevant object rank. Two hits with the same matched_fields can still differ: the score is rarity-weighted, so matching a rare term is worth more than matching a common one. Use this whenever you have a question rather than an id, then follow up with get_entity.
입력 스키마
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 200,
"description": "What to look for, in the user's own words. Matched against titles, questions, claim text and tags; accents and apostrophes are ignored, so 'jose' finds 'José'."
},
"limit": {
"default": 10,
"description": "How many ranked hits to return, best first.",
"type": "integer",
"minimum": 1,
"maximum": 25
}
},
"required": [
"query"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}출력 스키마
{
"type": "object",
"properties": {
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"type": {
"type": "string"
},
"name": {
"type": "string"
},
"summary": {
"type": "string"
},
"tags": {
"type": "array",
"items": {
"type": "string"
}
},
"evidence_tier": {
"type": "string"
},
"confidence": {
"type": "number"
},
"last_verified": {
"type": "string"
},
"canonical_url": {
"type": "string"
},
"api_url": {
"type": "string"
},
"x": {
"description": "Indexed instance-specific attributes, grouped by namespace — the same fields api/index.json publishes. Absent when the instance declares none.",
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
},
"score": {
"type": "number",
"description": "BM25 relevance: each query term is weighted by how RARE it is in this corpus and by where it hits (name 3, tags 2, questions 2, body 1). A hit must also cover a minimum share of the question's information, measured in the same rarity weights — matching only common words does not qualify. Centrality (how many objects point at this one) breaks TIES ONLY and is never part of the score, so it cannot make an irrelevant object rank. Two hits with the same matched_fields can still differ: the score is rarity-weighted, so matching a rare term is worth more than matching a common one."
},
"matched_fields": {
"type": "array",
"items": {
"type": "string"
},
"description": "Which fields the query hit: name, tags, questions, summary, claims. Does NOT determine the score on its own."
},
"coverage": {
"type": "number",
"description": "Share of the question's information this object accounts for, weighted by term rarity. 1 means every meaningful word in the query is present; a low value with a high score means the object matched common words only."
}
},
"required": [
"id",
"type",
"name",
"summary",
"tags",
"evidence_tier",
"confidence",
"last_verified",
"canonical_url",
"api_url",
"score",
"matched_fields",
"coverage"
],
"additionalProperties": false
}
},
"total": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
}
},
"required": [
"results",
"total"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_entity(id)
Fetch one knowledge object by id, with its claims and the sources each claim cites. Use this once search, answer or get_topic has given you an id. An unknown id is not a dead end: the answer names near-miss ids you can retry with.
입력 스키마
{
"type": "object",
"properties": {
"id": {
"type": "string",
"minLength": 1,
"maxLength": 100,
"description": "The knowledge object's id, as returned by search, answer, get_topic or get_related — the last segment of its canonical URL."
}
},
"required": [
"id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}출력 스키마
{
"type": "object",
"properties": {
"found": {
"type": "boolean"
},
"entity": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"type": {
"type": "string"
},
"name": {
"type": "string"
},
"summary": {
"type": "string"
},
"tags": {
"type": "array",
"items": {
"type": "string"
}
},
"evidence_tier": {
"type": "string"
},
"confidence": {
"type": "number"
},
"last_verified": {
"type": "string"
},
"canonical_url": {
"type": "string"
},
"api_url": {
"type": "string"
},
"x": {
"description": "Indexed instance-specific attributes, grouped by namespace — the same fields api/index.json publishes. Absent when the instance declares none.",
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
},
"questions": {
"type": "array",
"items": {
"type": "string"
}
},
"claims": {
"type": "array",
"items": {
"type": "object",
"properties": {
"text": {
"type": "string"
},
"confidence": {
"type": "number"
},
"sources": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"url": {
"type": "string"
}
},
"required": [
"id",
"title"
],
"additionalProperties": false
}
}
},
"required": [
"text",
"confidence",
"sources"
],
"additionalProperties": false
}
},
"body": {
"type": "string"
},
"media": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"url": {
"type": "string"
},
"alt": {
"type": "string"
},
"credit": {
"type": "string"
},
"license_spdx": {
"type": "string"
},
"caption": {
"type": "string"
},
"supports": {
"type": "string"
},
"width": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
"height": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
"permissions": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "boolean"
}
}
},
"required": [
"id",
"url",
"alt",
"credit",
"license_spdx",
"permissions"
],
"additionalProperties": false
}
}
},
"required": [
"id",
"type",
"name",
"summary",
"tags",
"evidence_tier",
"confidence",
"last_verified",
"canonical_url",
"api_url",
"questions",
"claims",
"media"
],
"additionalProperties": false
},
"recovery": {
"type": "object",
"properties": {
"did_you_mean": {
"type": "array",
"items": {
"type": "string"
}
},
"available_count": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
"available": {
"type": "array",
"items": {
"type": "string"
}
},
"available_truncated": {
"type": "boolean"
},
"next_tool": {
"type": "string"
},
"hint": {
"type": "string"
}
},
"required": [
"available_count",
"available",
"next_tool",
"hint"
],
"additionalProperties": false
}
},
"required": [
"found"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_topic(tag, limit, cursor)
List the knowledge objects carrying a tag (topics are content-backed tags). PAGED: 25 objects by default, 200 at most, and a response budget of about 64 KB per call — a page over budget comes back shorter WITH a next_cursor, never truncated. Read next_cursor and call again to continue, and its absence means you have the last page. Use this to browse a known topic; use search when you have a question rather than a tag, and get_overview to see which tags exist. An unknown tag comes back with the topics that do exist, so a miss still moves you forward.
입력 스키마
{
"type": "object",
"properties": {
"tag": {
"type": "string",
"minLength": 1,
"maxLength": 100,
"description": "The topic to list, spelled exactly as get_overview publishes it. Every published topic has objects under it, so an empty answer means the topic does not exist."
},
"limit": {
"description": "How many objects to return. Defaults to 25.",
"type": "integer",
"minimum": 1,
"maximum": 200
},
"cursor": {
"description": "Continue from a previous call: pass the next_cursor it returned. Opaque; do not construct one.",
"type": "string",
"minLength": 1,
"maxLength": 200
}
},
"required": [
"tag"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}출력 스키마
{
"type": "object",
"properties": {
"tag": {
"type": "string"
},
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"type": {
"type": "string"
},
"name": {
"type": "string"
},
"summary": {
"type": "string"
},
"tags": {
"type": "array",
"items": {
"type": "string"
}
},
"evidence_tier": {
"type": "string"
},
"confidence": {
"type": "number"
},
"last_verified": {
"type": "string"
},
"canonical_url": {
"type": "string"
},
"api_url": {
"type": "string"
},
"x": {
"description": "Indexed instance-specific attributes, grouped by namespace — the same fields api/index.json publishes. Absent when the instance declares none.",
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
}
},
"required": [
"id",
"type",
"name",
"summary",
"tags",
"evidence_tier",
"confidence",
"last_verified",
"canonical_url",
"api_url"
],
"additionalProperties": false
}
},
"total": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991,
"description": "How many objects carry this tag, before paging."
},
"returned": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
"next_cursor": {
"description": "Pass to the next call to continue. ABSENT means this was the last page.",
"type": "string"
},
"recovery": {
"type": "object",
"properties": {
"did_you_mean": {
"type": "array",
"items": {
"type": "string"
}
},
"available_count": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
"available": {
"type": "array",
"items": {
"type": "string"
}
},
"available_truncated": {
"type": "boolean"
},
"next_tool": {
"type": "string"
},
"hint": {
"type": "string"
}
},
"required": [
"available_count",
"available",
"next_tool",
"hint"
],
"additionalProperties": false
}
},
"required": [
"tag",
"results",
"total",
"returned"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢answer(question)
Answer a question from the corpus, or refuse. Returns only the claims that bear on the question, each with the sources it cites and its editorial confidence. When the corpus cannot answer, answered is false and abstention_reason plus missing_topics say what was not covered — a refusal is a real result here, not an error. Use this when the user asked a question in words; use search when you want to see the candidates yourself.
입력 스키마
{
"type": "object",
"properties": {
"question": {
"type": "string",
"minLength": 3,
"maxLength": 300,
"description": "The question to answer, in the words the user asked it."
}
},
"required": [
"question"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}출력 스키마
{
"type": "object",
"properties": {
"answered": {
"type": "boolean"
},
"matched_question": {
"description": "The stored question this was matched to, when the answer came from one.",
"type": "string"
},
"match_confidence": {
"description": "How well the answer fits the QUESTION — retrieval confidence, not editorial. Never confuse it with a claim's own confidence, which is how much the corpus stands behind the statement.",
"type": "number"
},
"match_score": {
"type": "number"
},
"match_threshold": {
"type": "number",
"description": "The coverage this corpus requires before it will answer at all."
},
"coverage": {
"description": "Share of the question's information the winning object accounts for, weighted by term rarity.",
"type": "number"
},
"margin": {
"description": "Relative gap between the best candidate and the runner-up. A small margin means the corpus cannot tell them apart.",
"type": "number"
},
"matched_fields": {
"type": "array",
"items": {
"type": "string"
}
},
"missing_topics": {
"type": "array",
"items": {
"type": "string"
},
"description": "Meaningful words in the question that appear nowhere in the winning object — the gap, named."
},
"abstention_reason": {
"description": "Why the corpus declined: empty_query, no_candidates, below_coverage, ambiguous_candidates or no_intent_match.",
"type": "string"
},
"candidates": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"score": {
"type": "number"
},
"coverage": {
"type": "number"
}
},
"required": [
"id",
"score",
"coverage"
],
"additionalProperties": false
},
"description": "Near misses, so a refusal is still a lead. Present whether or not the question was answered."
},
"entity": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"type": {
"type": "string"
},
"name": {
"type": "string"
},
"summary": {
"type": "string"
},
"tags": {
"type": "array",
"items": {
"type": "string"
}
},
"evidence_tier": {
"type": "string"
},
"confidence": {
"type": "number"
},
"last_verified": {
"type": "string"
},
"canonical_url": {
"type": "string"
},
"api_url": {
"type": "string"
},
"x": {
"description": "Indexed instance-specific attributes, grouped by namespace — the same fields api/index.json publishes. Absent when the instance declares none.",
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
}
},
"required": [
"id",
"type",
"name",
"summary",
"tags",
"evidence_tier",
"confidence",
"last_verified",
"canonical_url",
"api_url"
],
"additionalProperties": false
},
"claims": {
"type": "array",
"items": {
"type": "object",
"properties": {
"text": {
"type": "string"
},
"confidence": {
"type": "number"
},
"sources": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"url": {
"type": "string"
}
},
"required": [
"id",
"title"
],
"additionalProperties": false
}
},
"relevance": {
"type": "number"
}
},
"required": [
"text",
"confidence",
"sources",
"relevance"
],
"additionalProperties": false
}
}
},
"required": [
"answered",
"match_threshold",
"missing_topics",
"candidates"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_sources(object_id, tier, host, accessed_since, limit, ...)
The instance's source registry — each entry with its evidence tier, reliability and access date. PAGED: 25 entries by default, 200 at most, and a response budget of about 64 KB per call — a page over budget comes back shorter WITH a next_cursor, never truncated. Read next_cursor and call again to continue; its absence means you have the last page. Filter by object_id, tier, host or accessed_since to avoid paging through a registry you do not need. Use this when you need the registry entry behind a citation, or a sample of the whole registry to judge the corpus before trusting it; get_entity already tells you which sources a claim cites.
입력 스키마
{
"type": "object",
"properties": {
"object_id": {
"description": "Restrict the answer to the sources cited by this knowledge object. Omit it to page the whole registry.",
"type": "string",
"minLength": 1,
"maxLength": 100
},
"tier": {
"description": "Only sources of this evidence tier, spelled exactly as get_sources reports it.",
"type": "string",
"minLength": 1,
"maxLength": 60
},
"host": {
"description": "Only sources whose URL is served by this host, compared without a leading www. A source with no URL never matches.",
"type": "string",
"minLength": 1,
"maxLength": 120
},
"accessed_since": {
"description": "Only sources accessed on or after this ISO date (YYYY-MM-DD).",
"type": "string",
"minLength": 4,
"maxLength": 10
},
"limit": {
"description": "How many entries to return. Defaults to 25.",
"type": "integer",
"minimum": 1,
"maximum": 200
},
"cursor": {
"description": "Continue from a previous call: pass the next_cursor it returned. Opaque; do not construct one.",
"type": "string",
"minLength": 1,
"maxLength": 200
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}출력 스키마
{
"type": "object",
"properties": {
"found": {
"type": "boolean"
},
"sources": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"url": {
"type": "string"
},
"tier": {
"type": "string"
},
"reliability": {
"type": "number"
},
"accessed": {
"type": "string"
}
},
"required": [
"id",
"title",
"tier",
"reliability",
"accessed"
],
"additionalProperties": false
}
},
"total": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991,
"description": "How many sources matched the filters, before paging."
},
"returned": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
"next_cursor": {
"description": "Pass to the next call to continue. ABSENT means this was the last page.",
"type": "string"
},
"recovery": {
"type": "object",
"properties": {
"did_you_mean": {
"type": "array",
"items": {
"type": "string"
}
},
"available_count": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
"available": {
"type": "array",
"items": {
"type": "string"
}
},
"available_truncated": {
"type": "boolean"
},
"next_tool": {
"type": "string"
},
"hint": {
"type": "string"
}
},
"required": [
"available_count",
"available",
"next_tool",
"hint"
],
"additionalProperties": false
}
},
"required": [
"found",
"sources",
"total",
"returned"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_related(id, limit, cursor)
Graph neighbours of an object: outgoing and incoming relations, each with its relation type. PAGED: 25 relations by default, 200 at most, and a response budget of about 64 KB per call — a page over budget comes back shorter WITH a next_cursor, never truncated. One cursor walks both directions, outgoing first; its absence means you have the last page. Use this after get_entity to widen an answer with adjacent objects. It walks one hop from an id you already have — use search when you have a question and no starting object.
입력 스키마
{
"type": "object",
"properties": {
"id": {
"type": "string",
"minLength": 1,
"maxLength": 100,
"description": "The knowledge object to walk out from, by id."
},
"limit": {
"description": "How many relations to return, across both directions. Defaults to 25.",
"type": "integer",
"minimum": 1,
"maximum": 200
},
"cursor": {
"description": "Continue from a previous call: pass the next_cursor it returned. Opaque; do not construct one.",
"type": "string",
"minLength": 1,
"maxLength": 200
}
},
"required": [
"id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}출력 스키마
{
"type": "object",
"properties": {
"found": {
"type": "boolean"
},
"outgoing": {
"type": "array",
"items": {
"type": "object",
"properties": {
"rel": {
"type": "string"
},
"entity": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"type": {
"type": "string"
},
"name": {
"type": "string"
},
"summary": {
"type": "string"
},
"tags": {
"type": "array",
"items": {
"type": "string"
}
},
"evidence_tier": {
"type": "string"
},
"confidence": {
"type": "number"
},
"last_verified": {
"type": "string"
},
"canonical_url": {
"type": "string"
},
"api_url": {
"type": "string"
},
"x": {
"description": "Indexed instance-specific attributes, grouped by namespace — the same fields api/index.json publishes. Absent when the instance declares none.",
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
}
},
"required": [
"id",
"type",
"name",
"summary",
"tags",
"evidence_tier",
"confidence",
"last_verified",
"canonical_url",
"api_url"
],
"additionalProperties": false
}
},
"required": [
"rel",
"entity"
],
"additionalProperties": false
}
},
"incoming": {
"type": "array",
"items": {
"type": "object",
"properties": {
"rel": {
"type": "string"
},
"entity": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"type": {
"type": "string"
},
"name": {
"type": "string"
},
"summary": {
"type": "string"
},
"tags": {
"type": "array",
"items": {
"type": "string"
}
},
"evidence_tier": {
"type": "string"
},
"confidence": {
"type": "number"
},
"last_verified": {
"type": "string"
},
"canonical_url": {
"type": "string"
},
"api_url": {
"type": "string"
},
"x": {
"description": "Indexed instance-specific attributes, grouped by namespace — the same fields api/index.json publishes. Absent when the instance declares none.",
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
}
},
"required": [
"id",
"type",
"name",
"summary",
"tags",
"evidence_tier",
"confidence",
"last_verified",
"canonical_url",
"api_url"
],
"additionalProperties": false
}
},
"required": [
"rel",
"entity"
],
"additionalProperties": false
}
},
"total": {
"description": "How many relations this object has in both directions, before paging.",
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
"returned": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
"next_cursor": {
"description": "Pass to the next call to continue. ABSENT means this was the last page.",
"type": "string"
},
"recovery": {
"type": "object",
"properties": {
"did_you_mean": {
"type": "array",
"items": {
"type": "string"
}
},
"available_count": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
"available": {
"type": "array",
"items": {
"type": "string"
}
},
"available_truncated": {
"type": "boolean"
},
"next_tool": {
"type": "string"
},
"hint": {
"type": "string"
}
},
"required": [
"available_count",
"available",
"next_tool",
"hint"
],
"additionalProperties": false
}
},
"required": [
"found"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_latest(limit)
Most recently verified knowledge objects (freshness signal). Use this to judge how current the corpus is, or to see what changed since you last read it. It ranks by verification date and ignores your topic entirely — use search or get_topic when you want objects that are relevant rather than recent.
입력 스키마
{
"type": "object",
"properties": {
"limit": {
"default": 10,
"description": "How many recently verified objects to return, newest verification first.",
"type": "integer",
"minimum": 1,
"maximum": 25
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}출력 스키마
{
"type": "object",
"properties": {
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"type": {
"type": "string"
},
"name": {
"type": "string"
},
"summary": {
"type": "string"
},
"tags": {
"type": "array",
"items": {
"type": "string"
}
},
"evidence_tier": {
"type": "string"
},
"confidence": {
"type": "number"
},
"last_verified": {
"type": "string"
},
"canonical_url": {
"type": "string"
},
"api_url": {
"type": "string"
},
"x": {
"description": "Indexed instance-specific attributes, grouped by namespace — the same fields api/index.json publishes. Absent when the instance declares none.",
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
}
},
"required": [
"id",
"type",
"name",
"summary",
"tags",
"evidence_tier",
"confidence",
"last_verified",
"canonical_url",
"api_url"
],
"additionalProperties": false
}
},
"total": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
}
},
"required": [
"results",
"total"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_overview
Corpus overview: what this instance knows, counts by type, published tags, freshness. Use this first when you land here and do not yet know whether this corpus can answer your question.
입력 스키마
{
"type": "object",
"properties": {},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}출력 스키마
{
"type": "object",
"properties": {
"instance": {
"type": "string"
},
"description": {
"type": "string"
},
"total_objects": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
"by_type": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
}
},
"tags": {
"type": "array",
"items": {
"type": "string"
}
},
"newest_verification": {
"type": "string"
},
"oldest_verification": {
"type": "string"
},
"total_media": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
}
},
"required": [
"instance",
"description",
"total_objects",
"by_type",
"tags",
"newest_verification",
"oldest_verification",
"total_media"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢compare(ids)
Two to six knowledge objects side by side: their cards, every indexed attribute as a matrix (the same fields api/index.json publishes, null where an object does not say), the tags they share, the relations that run between them, the neighbours they have in common, and each one's claims with sources and confidence. Use this when the question is 'X vs Y', 'is X the same as Y' or 'how does X differ from Y' — search or get_topic first if you only have names, then pass the ids. An unknown id lands in `missing` with a near-miss suggestion and the rest are still compared.
입력 스키마
{
"type": "object",
"properties": {
"ids": {
"minItems": 2,
"maxItems": 6,
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 100
},
"description": "Two to six knowledge object ids, as returned by search, get_topic or get_related, in the order you want the columns."
}
},
"required": [
"ids"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}출력 스키마
{
"type": "object",
"properties": {
"found": {
"type": "boolean",
"description": "True only when every id resolved."
},
"missing": {
"type": "array",
"items": {
"type": "string"
},
"description": "The ids that resolved to nothing, in the order asked."
},
"objects": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"type": {
"type": "string"
},
"name": {
"type": "string"
},
"summary": {
"type": "string"
},
"tags": {
"type": "array",
"items": {
"type": "string"
}
},
"evidence_tier": {
"type": "string"
},
"confidence": {
"type": "number"
},
"last_verified": {
"type": "string"
},
"canonical_url": {
"type": "string"
},
"api_url": {
"type": "string"
},
"x": {
"description": "Indexed instance-specific attributes, grouped by namespace — the same fields api/index.json publishes. Absent when the instance declares none.",
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
}
},
"required": [
"id",
"type",
"name",
"summary",
"tags",
"evidence_tier",
"confidence",
"last_verified",
"canonical_url",
"api_url"
],
"additionalProperties": false
}
},
"facets": {
"type": "array",
"items": {
"type": "object",
"properties": {
"field": {
"type": "string",
"description": "namespace.field, as declared in the instance blueprint"
},
"values": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {},
"description": "Value per object id; null where that object does not carry the field."
}
},
"required": [
"field",
"values"
],
"additionalProperties": false
}
},
"shared_tags": {
"type": "array",
"items": {
"type": "string"
}
},
"relations_between": {
"type": "array",
"items": {
"type": "object",
"properties": {
"from": {
"type": "string"
},
"rel": {
"type": "string"
},
"to": {
"type": "string"
}
},
"required": [
"from",
"rel",
"to"
],
"additionalProperties": false
}
},
"shared_neighbours": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"name": {
"type": "string"
},
"canonical_url": {
"type": "string"
},
"via": {
"type": "array",
"items": {
"type": "object",
"properties": {
"from": {
"type": "string"
},
"rel": {
"type": "string"
}
},
"required": [
"from",
"rel"
],
"additionalProperties": false
}
}
},
"required": [
"id",
"name",
"canonical_url",
"via"
],
"additionalProperties": false
}
},
"claims": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "array",
"items": {
"type": "object",
"properties": {
"text": {
"type": "string"
},
"confidence": {
"type": "number"
},
"sources": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"url": {
"type": "string"
}
},
"required": [
"id",
"title"
],
"additionalProperties": false
}
}
},
"required": [
"text",
"confidence",
"sources"
],
"additionalProperties": false
}
},
"description": "Every compared object's claims, keyed by object id."
},
"recovery": {
"type": "object",
"properties": {
"did_you_mean": {
"type": "array",
"items": {
"type": "string"
}
},
"available_count": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
"available": {
"type": "array",
"items": {
"type": "string"
}
},
"available_truncated": {
"type": "boolean"
},
"next_tool": {
"type": "string"
},
"hint": {
"type": "string"
}
},
"required": [
"available_count",
"available",
"next_tool",
"hint"
],
"additionalProperties": false
}
},
"required": [
"found",
"missing",
"objects",
"facets",
"shared_tags",
"relations_between",
"shared_neighbours",
"claims"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}커뮤니티
증거
최근 관측
검증됨버전이 기록되지 않음도구 9개
검증됨버전이 기록되지 않음도구 9개