Korean accounting standards (K-IFRS, K-GAAP, audit, ICFR) and official Q&A, cited by paragraph.
Scored across 10 tools
Most tools have distinct purposes, but fetch overlaps with specialized getters (get_paragraphs, get_qna, get_standard) because fetch can retrieve any id, including paragraphs and Q&As. An agent might be unsure whether to use fetch or the more targeted tool when both are applicable. However, the descriptions clearly state the required inputs, which mostly resolves the ambiguity.
The set follows a mostly consistent verb_noun pattern (get_paragraphs, get_qna, get_related, get_standard, get_topic, list_audit_cases, list_standards, verify_quote). The only deviations are the bare verbs fetch and search, which are common and readable but break the pattern slightly.
10 tools are well-scoped for an accounting knowledge base covering standards, Q&A, audit cases, articles, and topics. Each tool has a clear, non-redundant role, and the count falls within the ideal 3-15 range.
The surface covers core retrieval, cross-referencing, verification, and listing for standards and audit cases, which is strong for a read-only domain. Minor gaps exist: there is no dedicated tool to list all Q&A or all articles (though search can find them), and no bulk browsing for those collections.
search 등이 반환한 id(para:… / qna:… / std:… / article:…)로 해당 문단·질의회신·기준서 목차·실무해설의 전문 마크다운을 조회. 결과는 이용자 질의에 대한 조회 목적으로만 제공되며 원문 저작권은 제정·발행기관에 있다. 인용 시 응답의 출처 URL 을 표기할 것.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | search 결과의 id (예: 'para:ifrs/1116/main/p22') |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the safe read-only/idempotent/non-destructive profile, so the bar is lower. The description adds genuinely non-structural context: results are limited to inquiry purposes, copyright belongs to the publishing body, and the source URL must be cited — real behavioral/policy guidance absent from annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, front-loaded with the retrieval action and id syntax before the usage policy. Each sentence earns its place, though the copyright/citation clause is somewhat verbose relative to a lookup tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, but the description states the return is full markdown text and explains the id taxonomy and citation requirement. Complete enough for a single-parameter fetch; the only gap is the missing disambiguation against the near-identical sibling getters.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the single id parameter is self-contained, so the baseline is high. The description still adds value beyond the schema by enumerating all four id prefixes (para/qna/std/article) and the corresponding entity types, whereas the schema example only shows 'para:'.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (조회/fetch) and resource (문단·질의회신·기준서 목차·실무해설의 전문 마크다운) keyed by id, with the id prefixes enumerated. The purpose is unmistakable, though it does not explicitly distinguish itself from the overlapping get_paragraphs / get_qna / get_standard siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It establishes the entry condition ('search 등이 반환한 id로'), implying fetch is called after search to expand a hit into full text. However, it never says when to prefer fetch over the type-specific siblings (get_paragraphs, get_qna, get_standard), leaving the routing decision to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
기준서의 특정 문단들을 번호로 조회 (예: std='1116', paras=['22','B34']). 적용지침(B)·결론도출근거(BC) 문단도 토큰으로 자동 해석. 결과는 이용자 질의에 대한 조회 목적으로만 제공되며 원문 저작권은 제정·발행기관에 있다. 인용 시 응답의 출처 URL 을 표기할 것.
| Name | Required | Description | Default |
|---|---|---|---|
| std | Yes | 기준서 번호 (예: '1116', kgaap 은 '13') | |
| paras | Yes | 문단 번호 목록 (예: ['22','한54.2','B34','BC78']) | |
| domain | No | 기본값 ifrs |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower, and the description still adds real behavior: auto-interpretation of 적용지침(B) and 결론도출근거(BC) paragraph tokens, plus the attribution/source-URL requirement on citation. It does not describe batch behavior or failure modes, keeping it short of a 5.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with purpose and a worked example, then the token-resolution behavior, then the copyright/attribution note. Every sentence is short and non-redundant, though the boilerplate legal sentence is the least essential part.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With annotations covering safety, 100% schema coverage, and no output schema, the description is nearly complete for a simple lookup; it even mentions that the response carries a source URL. It stops short of explaining return structure or how missing paragraph numbers are handled.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3; the description's examples for std and paras largely repeat the schema. The one genuinely additive note is that B/BC tokens in paras are auto-resolved, which clarifies accepted values beyond the schema's example list.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('기준서의 특정 문단들을 번호로 조회') with concrete examples (std='1116', paras=['22','B34']). An agent can immediately tell it is a targeted paragraph lookup rather than a whole-standard retrieval, though it never names the get_standard sibling it most closely resembles.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is implied by the example and the by-number retrieval framing, but no explicit when-to-use/when-not or alternative routing (e.g., get_standard for full text, search for discovery, fetch) is given. The agent must infer the boundary from the sibling names alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
질의회신·감리지적사례 전문 조회 (slug 는 search 결과 또는 페이지 URL 마지막 경로). 결과는 이용자 질의에 대한 조회 목적으로만 제공되며 원문 저작권은 제정·발행기관에 있다. 인용 시 응답의 출처 URL 을 표기할 것.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | 질의회신 슬러그 (예: 'SSI-38683') | |
| domain | No | 기본값 ifrs |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish a safe read-only, idempotent, closed-world operation. The description adds genuinely new context beyond them: the result is licensed for lookup purposes only, copyright belongs to the issuing body, and citations must include the source URL. That is real behavioral/attribution guidance.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with the purpose, then supporting details in one compact paragraph with no filler sentences. The legal/citation clause is somewhat tangential but still earns its place as usage context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, yet the description deliberately does not need to explain return values; it covers purpose, slug sourcing, and licensing. For a simple read-only lookup with full schema coverage, this is nearly complete, missing only explicit sibling routing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3, but the description goes beyond the schema by explaining where the slug originates (search results or the URL's final path segment). This adds invocation value the schema alone does not supply.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource: full-text retrieval of Q&A responses and audit inspection findings, which is distinct from siblings like get_standard or get_paragraphs. However, it does not explicitly differentiate itself from the other retrieval siblings (fetch, search), so it falls short of a 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It tells the agent where the slug comes from (search results or the last path segment of a page URL), which is actionable invocation context. But it gives no when-to-use/when-not guidance and never names an alternative sibling, so usage is only implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
기준서의 목차(섹션·문단 범위)와 메타데이터 조회. section 지정 시 해당 섹션 본문 전체를 반환. 전문 마크다운은 응답의 .md URL 로도 제공. 결과는 이용자 질의에 대한 조회 목적으로만 제공되며 원문 저작권은 제정·발행기관에 있다. 인용 시 응답의 출처 URL 을 표기할 것.
| Name | Required | Description | Default |
|---|---|---|---|
| std | Yes | 기준서 번호 (예: '1116') | |
| domain | No | 기본값 ifrs | |
| section | No | 섹션 제목 (목차에 나온 제목, 부분 일치 허용) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnlyHint, idempotentHint, openWorldHint=false, and destructiveHint=false. The description adds useful behavior beyond those annotations: that a section request returns the full section body, that full markdown is exposed through a .md URL, and that citation/source attribution is required.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The core retrieval behavior and section behavior are front-loaded and concise. The copyright and citation sentences are somewhat ancillary but relevant to responsible use of the returned content, so they mostly earn their place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a read-only lookup tool with rich annotations, a complete input schema, and no output schema, the description covers the essential return behavior, including TOC/metadata, full section retrieval, and the .md URL. It is nearly complete, though alternative-tool guidance is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description still adds meaning beyond the schema by explaining the effect of the optional section parameter: specifying it returns that section's full text rather than only the TOC/metadata.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb and resource: retrieving a standard's table of contents, section/paragraph ranges, and metadata. It also clarifies that specifying section returns the full section body. However, it does not explicitly distinguish this tool from siblings such as get_paragraphs or list_standards.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage by explaining that a section can be specified to get the full section text, and that full markdown is available via a .md URL. But it gives no explicit when-to-use or when-not-to-use guidance relative to fetch, search, get_paragraphs, or list_standards.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
회계 주제(예: '자산손상', '리스', '수익')의 정의·관련어, 핵심 기준서 문단 범위, 대표 질의회신·감리지적사례·실무해설을 한 번에 반환. 주제명·관련어·slug 로 조회하며, topic 을 생략하면 전체 토픽 목록. 결과는 이용자 질의에 대한 조회 목적으로만 제공되며 원문 저작권은 제정·발행기관에 있다. 인용 시 응답의 출처 URL 을 표기할 것.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | 질의회신·실무해설 종류별 최대 건수, 기본 8 | |
| topic | No | 주제명·관련어·slug (예: '자산손상', '손상차손', 'asset-impairment') |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint/idempotent/non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: it discloses the aggregated multi-source return, the copyright restriction, and the citation obligation to include source URLs — none of which the annotations convey.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three dense sentences, front-loaded with the return contents before the query mechanics and the legal/citation caveat. Every sentence carries information, though the copyright/citation sentence could be tightened.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description carries the burden of describing the return payload, and it does so thoroughly by enumerating the result categories. It also covers query modes, the list-all fallback, and citation requirements, leaving no critical gap for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3, but the description adds meaning the schema does not: it clarifies that 'topic' accepts names, related terms, or slugs (with examples) and that omitting it switches to a list-all mode, which is default-behavior information absent from the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource (get_topic) and enumerates exactly what is returned: topic definition/related terms, standard paragraph ranges, representative Q&A, audit findings, and practice commentary. This clearly separates it from siblings like get_paragraphs, get_qna, get_standard, and list_standards, which each cover only one of those slices.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explains the lookup keys (topic name, related term, slug) and the fallback behavior when 'topic' is omitted (returns the full topic list). It does not name an explicit alternative tool or a when-not-to-use condition, so it falls short of full routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
금융감독원·한국공인회계사회 감리지적사례를 계정·위반유형·기관·연도·키워드로 걸러 최근 순 목록을 반환. 조건 없이 호출하면 계정·위반유형 분류와 건수를 반환. 목록의 id 를 fetch 에 넘기면 사례 전문. 결과는 이용자 질의에 대한 조회 목적으로만 제공되며 원문 저작권은 제정·발행기관에 있다. 인용 시 응답의 출처 URL 을 표기할 것.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | 기본 20 | |
| query | No | 제목·본문 키워드 (부분 일치) | |
| source | No | 기관 — '금감원' 또는 '한공회' | |
| account | No | 계정·쟁점 (부분 일치, 예: '재고자산', '매출') | |
| year_to | No | 종료 연도 | |
| violation | No | 위반유형 (부분 일치, 예: '과대계상', '주석 미기재') | |
| year_from | No | 시작 연도 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world). The description adds genuine behavioral context the annotations cannot: two distinct return modes depending on whether filters are supplied, plus the citation/copyright obligation. It does not describe pagination or ordering mechanics beyond '최근 순'.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Core behavior (list, no-filter mode, fetch hand-off) is front-loaded in the first two sentences. The citation/copyright sentences are longer than the functional core but carry legitimate usage obligations, so they earn their place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description compensates by explaining both return shapes (filtered list vs. classification/counts) and that full text requires fetch. It is essentially complete for correct invocation, missing only minor details like default limit or pagination notes.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema fully documents all 7 parameters. The description recaps the filterable dimensions (계정·위반유형·기관·연도·키워드) but adds no syntax or format detail beyond the schema, so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb and resource (감리지적사례 목록 반환) plus the filterable dimensions, and explicitly contrasts itself with the 'fetch' sibling for full case text. An agent can distinguish this list tool from fetch without opening either schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explains a clear non-obvious calling mode (no conditions returns classification and counts) and routes the agent to fetch with an id for full text. No explicit 'when not to use' or mention of the other siblings (search, get_qna), but the primary alternative is covered.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
도메인의 기준서 전체 목록 (번호·제목·문단수·URL). 결과는 이용자 질의에 대한 조회 목적으로만 제공되며 원문 저작권은 제정·발행기관에 있다. 인용 시 응답의 출처 URL 을 표기할 것.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | No | 기본값 ifrs |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the safe-read profile (readOnly, idempotent, non-destructive, closed-world), so the safety bar is low. The description adds genuinely non-structured context: the exact result payload (번호·제목·문단수·URL) and a citation obligation requiring the source URL to be surfaced to the user. It says nothing about result size or pagination, but the added licensing/citation behavior is real value beyond the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with the payload fields, then two short constraint sentences. Every sentence carries information, though the copyright/citation sentences could be compressed into one without loss.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description correctly enumerates the returned fields, and annotations cover the safety profile. The remaining gap is the lack of differentiation from related retrieval tools and any hint about result volume, but for a single-optional-param list tool it is close to sufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the schema itself documents the enum values and the 'ifrs' default, so the baseline is 3. The description conveys only that results are scoped to 'a domain', adding no enum values, defaults, or behavior for an omitted parameter beyond what the schema states.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb+resource+scope: the full list of standards in a domain (번호·제목·문단수·URL). That is clearly distinct from get_standard/get_paragraphs conceptually, but the description never names the siblings, so the agent must infer the split between 'list all' and 'fetch one' on its own.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The only usage statement is a licensing restriction ('조회 목적으로만 제공'), not tool-selection guidance. There is no indication of when to prefer this over search, get_standard, or get_paragraphs, which are all plausible alternatives for finding standards.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
회계위키 전체(기준서 문단·질의회신·감리지적사례·실무해설)에서 키워드 검색. 결과의 id 를 fetch 에 넘기면 전문을 얻는다. 여러 어절은 AND 매칭. 결과는 이용자 질의에 대한 조회 목적으로만 제공되며 원문 저작권은 제정·발행기관에 있다. 인용 시 응답의 출처 URL 을 표기할 것.
| Name | Required | Description | Default |
|---|---|---|---|
| std | No | 기준서 번호로 한정 (예: '1116') | |
| kind | No | standard: 기준서 문단만, qna: 질의회신·감리사례만, article: 실무해설만 | |
| limit | No | 기본 10 | |
| query | Yes | 검색어 (예: '리스 변경 회계처리') | |
| domain | No | 도메인 필터 — 생략 시 전체 도메인 검색 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: multi-word queries are AND-matched, results carry ids for fetch, and there are copyright/citation obligations on the output.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with the core purpose and the id→fetch workflow; every sentence carries weight (search scope, AND semantics, copyright/citation). Slightly dense but no filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description compensates by telling the agent that results contain ids usable with fetch, and adds the citation requirement. It stops short of describing result shape (fields, ranking) or pagination, but is sufficient for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description adds one semantic not present in the schema — that multiple whitespace-separated terms are combined with AND — which directly affects how the query parameter behaves.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (키워드 검색) and enumerates the corpus it searches (기준서 문단·질의회신·감리지적사례·실무해설). It also explicitly distinguishes itself from the sibling fetch by describing the two-step id→fetch workflow.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives clear routing guidance: search here by keyword, then pass the returned id to fetch for full text. It does not name when to prefer siblings like get_paragraphs or get_qna over a keyword search, so it stops short of a full 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
기준서 문구 인용이 원문과 일치하는지 대조. 공백·문장부호 차이는 무시하고 일치(exact)·표현 차이(near)·부분 일치(partial)·불일치(mismatch)로 판정하며, 일치하지 않으면 가장 가까운 원문 문장과 그 문단을 반환. para 를 생략하면 기준서 전체에서 인용문이 있는 문단을 찾는다. 결과는 이용자 질의에 대한 조회 목적으로만 제공되며 원문 저작권은 제정·발행기관에 있다. 인용 시 응답의 출처 URL 을 표기할 것.
| Name | Required | Description | Default |
|---|---|---|---|
| std | Yes | 기준서 번호 (예: '1116', kgaap 은 '13') | |
| para | No | 문단 번호 (예: '22', 'B34') — 생략 시 기준서 전체 | |
| quote | Yes | 대조할 인용 문구 (5자 이상) | |
| domain | No | 기본값 ifrs |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safe-read profile (readOnly, idempotent, non-destructive), and the description adds substantial context beyond them: whitespace/punctuation are ignored, the four-way verdict taxonomy (exact/near/partial/mismatch), and that a mismatch returns the nearest original sentence plus its paragraph. It also discloses the legal/citation constraint (copyright and required source URL attribution).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The core matching behavior is front-loaded in the first sentence and each sentence carries information. The closing copyright/attribution sentences are somewhat boilerplate but do impose a real obligation on the caller, so they are not pure waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
There is no output schema, yet the description fully describes what is returned: a match verdict from a defined taxonomy, and on mismatch the closest sentence and its paragraph. Combined with annotations covering safety, an agent has everything needed to call and interpret this tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description restates the para-omission behavior already documented in the schema ('생략 시 기준서 전체') and adds no format or syntax detail beyond what the schema provides for std, quote, or domain.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Specific verb (대조/verify) plus specific resource (기준서 문구 인용 vs 원문), which is clearly distinct from siblings like search, fetch, and get_paragraphs that retrieve rather than verify. An agent can tell what this tool does without opening the schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives conditional behavior ('para 를 생략하면 기준서 전체에서 ... 찾는다'), which is genuine usage guidance for one parameter. However, it never states when to prefer this tool over retrieval siblings such as search or get_paragraphs, so routing guidance is only implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_relatedget_topiclist_audit_casessearch2 fields changedInput schema / properties / kind / descriptionPrevious value: -"standard: 기준서 문단만, qna: 질의회신·사례만"New value: +"standard: 기준서 문단만, qna: 질의회신·감리사례만, article: 실무해설만"Input schema / properties / kind / enumPrevious value: -[
- "standard",
- "qna"
-]New value: +[
+ "standard",
+ "qna",
+ "article"
+]verify_quotefetchget_paragraphsget_qnaget_standardlist_standardssearchFull-text search over K-IFRS/K-GAAP standards and KASB accounting Q&A for Korean accountants
Full-text search over FSS/FSC accounting supervision documents for Korean accounting professionals
Powerful OpenDART API-based Korean corporate disclosure tools for accounting professionals
Korean company disclosures in English: DART filings, financial statements, segments, 13F.
Add one secure layer between your agents and this server.