Skip to main content
Glama
dolseom

gongsi-mcp

by dolseom
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

공정위 공식 문답 + 매뉴얼 본문 검색

search_ftc_qna

Search Korean FTC Q&A and manual passages to provide official grounds for corporate disclosure compliance edge cases that rules alone cannot resolve.

Instructions

공정위가 배포한 해설서·FAQ·매뉴얼에서 추출한 공식 질의응답 430건 (2026. 4. 27. 공시 업무 매뉴얼 주요 사례 79건 포함)과 2026. 4. 27. 공시 업무 매뉴얼 4종 본문 (대규모내부거래·비상장사 중요사항·기업집단 현황공시 소속회사용/동일인용)을 함께 검색합니다 (키 불요). 규칙만으로 판정할 수 없는 경계사례에 공식 근거를 대는 용도입니다.

  • 문답은 results, 매뉴얼 본문 구절은 manualPassages(문서명·쪽·소제목·본문)로 돌려줍니다. 문답에 없는 규칙(대상에서 빠지는 거래·서식 작성 주체·공시 중복 시 갈음·제출 시각 등)은 매뉴얼 본문에만 있습니다

  • 검색어는 핵심 명사 위주가 잘 맞습니다. category 로 공시유형을 좁힐 수 있습니다

  • 매뉴얼 본문은 현행 원문이라 옛 문답과 다르면 매뉴얼이 우선합니다

  • ⚠️ 구판 문서(2008~2015)에는 **폐지된 기준(50억·기한 1일 등)**이 실려 있습니다 — 각 결과의 caveats 를 반드시 함께 읽고, 같은 주제의 2026 매뉴얼 문답(lit26-*)이 있으면 그쪽을 우선하세요

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNo문답 최대 결과 수 (기본 5)
queryYes검색어. 거래 상황을 키워드로: "발행어음 자동연장", "자회사 설립 출자", "퇴직연금 거래금액" 등. 질문 문장을 통째로 넣어도 됩니다
categoryNo공시유형 필터. internal_transaction=대규모내부거래(J001), unlisted_material=비상장사 중요사항(J005), group_status=기업집단현황(J004), subcontract=하도급대금 결제조건(J009). 생략하면 전체에서 검색. 매뉴얼 본문도 같은 공시유형의 매뉴얼로 좁힙니다 (하도급대금은 매뉴얼 본문이 없습니다)
manual_limitNo매뉴얼 본문 구절 최대 수 (기본 3, 0 이면 매뉴얼 검색 생략)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.4.0
    • changedInput schema / properties / category / description
      Previous value: -"공시유형 필터. internal_transaction=대규모내부거래(J001), unlisted_material=비상장사 중요사항(J005), group_status=기업집단현황(J004), subcontract=하도급대금 결제조건(J009). 생략하면 전체에서 검색"New value: +"공시유형 필터. internal_transaction=대규모내부거래(J001), unlisted_material=비상장사 중요사항(J005), group_status=기업집단현황(J004), subcontract=하도급대금 결제조건(J009). 생략하면 전체에서 검색. 매뉴얼 본문도 같은 공시유형의 매뉴얼로 좁힙니다 (하도급대금은 매뉴얼 본문이 없습니다)"
    • changedInput schema / properties / limit / description
      Previous value: -"최대 결과 수 (기본 5)"New value: +"문답 최대 결과 수 (기본 5)"
    • addedInput schema / properties / manual_limit
      Added value: +{
+  "description": "매뉴얼 본문 구절 최대 수 (기본 3, 0 이면 매뉴얼 검색 생략)",
+  "maximum": 10,
+  "minimum": 0,
+  "type": "integer"
+}
  2. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations the description carries the full burden and delivers: authentication need (no key required), output split between results and manualPassages (doc/page/subheading/body), a precedence rule (current manual text overrides older Q&A), and a staleness warning that 2008–2015 documents contain abolished thresholds with caveats to read. This is unusually rich behavioral disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads what the tool searches, then uses bullets for returns, search tips, precedence and the warning. Slightly verbose with the repeated '2026. 4. 27.' date and item counts, but nearly every sentence earns its place and the warning is well placed at the end.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema and no annotations, yet the description explains the return structure (results vs manualPassages and their fields), the precedence between old and new sources, and the caveat-reading requirement. Nothing an agent needs to call and interpret this tool correctly appears to be missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

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 real search strategy beyond the schema ('core nouns work best', questions can be pasted whole) and reiterates how category narrows both Q&A and manual scope. It adds meaning on top of the well-documented parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (search) and two precisely named resources (FTC official Q&A extracted from guides/FAQ/manuals, plus the bodies of four 2026 disclosure manuals), with the count (430 items) and scope made explicit. An agent can tell this apart from siblings like find_precedents (precedents) and search_disclosures (filed disclosures) 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.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a clear when-to-use condition: supplying official grounding for borderline cases that rules alone cannot decide, and notes that certain rule topics live only in manual bodies. It does not explicitly name alternatives or state when NOT to reach for it over find_precedents, so it falls 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.

Deploy Server

Other Tools