Skip to main content
Glama

지원사업 공고 조회

opendata__smes__notices

공공데이터포털에 개방된 중소기업 지원사업 공고(data.go.kr 15157820)를 분야와 해시태그로 골라 조회합니다. 공고마다 공고명, 소관기관, 지원분야, 신청기간, 지원대상, 사업개요, 신청방법, 문의처를 원문 그대로 notices 에 돌려주고 원문 링크(pblancUrl)와 출처 줄을 붙입니다. 요약이나 점수는 만들지 않습니다. 전체 건수는 total_count 에, 더 있으면 truncated 가 참이고 pageNo 로 다음 쪽을 조회합니다. 별도 연동 없이 사용할 수 있습니다. Files: a document generated from this result, as Excel (xlsx) only when requested in output_formats, listed in artifacts[] of the result with a download_url that works for 15 minutes; each file is kept for 7 days. If a link has expired, call xdata__job__result with the job_id from the result for fresh links. For an anonymous result, keep its private recovery_receipt and send it with the original job_id or pack_run_id to xdata__job__result. It grants access to that result only, until the original file retention expires. Do not publish it. Losing it cannot be repaired by signing up. The receipt also works if the client later signs in; it does not grant access to other results. Without a receipt, results require the original account and lane. For an authenticated call, generate and save request_idempotency_key before the first request. Reuse it with the same arguments only to recover that request after a lost response; use a new key for a new execution. Without it, calling again remains a new request. This optional key is not available to anonymous taste calls. Keep any provider-specific idempotency_key unchanged; it is a different field. 호출마다 토큰 1소진 요청 처리 시 XBOSS 작업을 생성하고 처리 결과를 저장합니다. 기관 원본의 조회 여부와 별개로 이 호출은 순수 읽기 전용이 아닙니다. 기관 데이터 변경은 도구별 실행 내용과 기존 확인 절차를 따릅니다.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "opendata__smes__notices"
  }
}

Input Schema

NameRequiredDescriptionDefault
fieldNo지원 분야(선택). 금융, 기술, 인력, 수출, 내수, 창업, 경영, 기타 가운데 하나(코드 01, 02, 03, 04, 05, 06, 07, 09 도 됩니다). 비우면 전 분야.
pageNoNo페이지 번호(선택, 기본 1).
hashtagsNo해시태그(선택). 지역이나 업종 같은 낱말 목록이며 하나라도 맞는 공고를 고릅니다(예: 서울, 제조업). 낱말 안에 공백은 넣지 않습니다.
noticeIdNo공고 ID(선택). 한 공고만 다시 조회할 때 notices 의 pblancId 값을 줍니다.
numOfRowsNo한 페이지 공고 수(선택, 기본 50).
output_formatsNoOptional. Also return this result as a file (Excel (xlsx)) in artifacts[] of the result. Omit it for data only.
request_idempotency_keyNoOptional same-request recovery key for authenticated calls; see the tool description.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, openWorldHint=true, and destructiveHint=false, and the description is consistent with them, explicitly warning that this call is not purely read-only because a XBOSS job is created and its result stored regardless of the source lookup. It further discloses token cost per call, xlsx artifact retention (15-minute download_url, 7-day file life), and recovery/idempotency semantics — real behavior beyond the annotations. The value is diluted by platform-wide boilerplate that reads as copy-paste rather than tool-specific detail.

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

Conciseness2/5

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

The front-loaded Korean sentences about filtering, returned fields, and pagination are tight and well ordered. But they are followed by a long block of generic platform boilerplate — artifact retention, recovery_receipt handling, idempotency-key reuse policy, provider key caveats — much of which is unrelated to a read-only public-data lookup and buries the tool-specific information.

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 no output schema, the description compensates by naming the returned fields (notices, total_count, truncated, pblancUrl), the pagination contract, and the side-effect/cost profile for a 7-parameter, zero-required-parameter tool. An agent has enough to call it correctly and to know what comes back and what it costs.

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

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every parameter (field, pageNo, hashtags, noticeId, numOfRows, output_formats, request_idempotency_key) is already documented inline with defaults and limits. The description adds only the notices->pblancId linkage for noticeId and the output_formats file behavior, both of which largely restate schema text; the baseline of 3 applies.

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 first two sentences state a specific verb and resource (query SME support-program notices from data.go.kr dataset 15157820), the filters used (field, hashtags), and the exact fields returned verbatim plus pblancUrl and a source line. It also explicitly scopes out sibling capabilities by saying no summaries or scores are produced, so an agent knows this is a raw-record lookup rather than an analysis tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

It gives operational context — usable without separate integration, pageNo for the next page, noticeId for re-fetching a single notice, and one token consumed per call — which implies when to reach for it. However there is no explicit when-not guidance and no named alternative among the many opendata__* siblings (e.g., other sanction/registry lookups), so routing still depends on the agent's own match of name to intent.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources