Skip to main content
Glama

공시 검색

search_disclosures

Search corporate disclosures with built-in FTC presets. Filter by company, date, report type, and collect full-period records in batch mode.

Instructions

공시를 검색합니다. 공정위 기업집단 공시 프리셋이 내장되어 있습니다 (ftc_all=공정위 전체, internal_transaction=대규모내부거래, group_status=기업집단현황, unlisted_material=비상장사 중요사항, public_interest_corp=공익법인, subcontract=하도급 결제조건).

  • mode:"page"(기본) = 한 페이지씩 조회. mode:"batch" = 기간 전체 전수 수집 (중복 제거·건수 집계 포함)

  • batch 가 한 번에 처리하기 큰 범위면 range_too_large 에러와 함께 분할 구간을 안내합니다 — 안내된 구간대로 나눠 다시 호출하세요

  • report_name_contains 로 보고서명을 거를 수 있습니다 (선례 검색: preset+["자금차입" 등])

  • 응답의 diagnostics 를 반드시 확인하세요 — truncated/partial_results 가 true 면 결과가 불완전합니다

  • 정정 이전 원본 접수분을 포함합니다 (last_report_only 기본 false — 지연 판정에 필수)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNopage(기본)=한 페이지 조회. batch=적응형 분할 전수 수집 — 규모가 크면 range_too_large 와 분할 안내를 반환
pageNomode:"page" 의 페이지 번호 (기본 1)
limitNomode:"batch" 응답에 실을 최대 행수 (기본 200). 수집·집계는 전수로 하고 응답만 자릅니다
queryNo회사명·종목코드(6자리)·corp_code(8자리)·법인등록번호(13자리). 동명 법인이 여럿이면 ambiguous_corp 에러와 후보 목록을 돌려줍니다
presetNo공정위 공시 프리셋. ftc_all=J 전체 / internal_transaction=대규모내부거래 / group_status=기업집단현황 / unlisted_material=비상장사 중요사항 / public_interest_corp=공익법인 / subcontract=하도급 결제조건
compactNotrue 면 schema+값 배열 형태로 토큰 30~40% 절감 (행이 많을 때 권장)
date_toNo조회 종료일 YYYYMMDD (기본: 오늘)
corp_clsNo법인구분 Y=유가 K=코스닥 N=코넥스 E=기타(비상장 대부분)
corp_codeNoDART 법인코드 8자리 — query 대신 직접 지정
date_fromNo조회 시작일 YYYYMMDD (기본: 30일 전)
page_sizeNo페이지당 건수 (기본·최대 100)
pblntf_tyNoDART 공시유형 원시 코드 (preset 과 동시 지정 불가)
last_report_onlyNo⚠️ 기본 false. true(최종보고서만)는 정정으로 대체된 원본 접수분을 지워 지연 판정이 불가능해집니다
pblntf_detail_tyNoDART 공시상세유형 원시 코드 (preset 과 동시 지정 불가)
report_name_containsNo보고서명 부분일치 필터 — 서버 필터가 아니라 수집 후 적용됩니다 (예: "자금차입", "기재정정")
Behavior5/5

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

No annotations exist, and the description carries the full burden. It discloses the batch de-duplication/counting behavior, range_too_large error with split guidance, diagnostics/truncation warning, post-collection filtering, and the inclusion of pre-correction filings — information not available in structured fields.

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

Conciseness5/5

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

Though dense, every sentence contributes: purpose, preset list, mode semantics, error recovery, filtering, diagnostics, and correction handling. It is front-loaded with the core action and structured with bullets for readability.

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?

With 15 optional parameters and no output schema, the description covers essential operational caveats: batch splitting, diagnostic checks, and correction inclusion. It also provides fallback guidance for ambiguous entities via schema references, making it complete for a tool of this complexity.

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 baseline is 3. The description adds behavioral semantics for mode (page vs batch full collection), report_name_contains (post-collection filter), and last_report_only (impact on delay judgment) beyond the schema's descriptions, pushing it to 4.

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?

The description opens with '공시를 검색합니다' — a specific verb and resource — and adds built-in FTC disclosure presets, clearly distinguishing it as a search tool. It goes beyond a restatement of the title by enumerating preset types and key search modes, establishing a distinct scope among siblings.

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?

It provides clear context for page vs batch modes, including when batch is appropriate for full collection and how to handle range_too_large errors. It also notes report_name_contains for precedent search, but does not explicitly contrast with sibling tools like find_precedents or read_disclosure.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/dolseom/gongsi-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server