Skip to main content
Glama

기업지원금 진단 v1

subsidy_pack__diagnosis_v1__generate

Composite subsidy diagnosis v1: runs the work24 사업주 사전진단 sweep (one step covering every gated 지원사업) plus opendata nts.status, then reports which 지원금 the workplace may apply for. The work24 leg replays a logged-in session. No account_link_id is needed here: each step finds its own institution link. Verdicts keep work24's four raw states: 조사후결정/오류 are reported as undetermined, never folded into eligible the way the work24 screen does. An optional third leg lists 지원사업 공고 whose application period has not closed, some opening later (opendata.smes.notices, verbatim notice fields with source line and original links; no summary or score) under notices; if that source is down the diagnosis still comes back and notices says it could not be read. Give notice_field or notice_hashtags to narrow the notices, which makes that leg required for this call. If computed is null the result could not be assembled: read computed_error for the reason and do not present the result as complete. Two shapes carry that case: this envelope with partial set to true (we fetched everything - the legs hold it - but could not calculate), or an error whose data carries the same envelope. partial is true whenever the result is incomplete, whether a leg failed or the calculation did. Files: a document generated from this result, as PDF 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 pack_run_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 Do not publish it.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. 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": "subsidy_pack__diagnosis_v1__generate"
  }
}

Input Schema

NameRequiredDescriptionDefault
biznoNo10-digit business registration number for nts.status
notice_fieldNo공고 지원 분야(선택). 금융, 기술, 인력, 수출, 내수, 창업, 경영, 기타 가운데 하나. 비우면 전 분야의 공고를 함께 봅니다.
output_formatsNo선택 입력입니다. 결과를 PDF 파일로도 받으려면 입력해 주세요. 파일은 결과의 artifacts[] 에 실립니다. 비워 두면 데이터만 받습니다.
programme_keysNoOptional subset of catalogue programme keys; omit to diagnose every 사전진단 사업.
idempotency_keyNoOptional outer idempotency key; leg keys are derived deterministically from this value.
notice_hashtagsNo공고 해시태그(선택). 지역이나 업종 같은 낱말 목록이며 하나라도 맞는 공고를 고릅니다(예: 서울, 제조업). 낱말 안에 공백은 넣지 않습니다.
application_yearNo신청시작연도 (defaults to the current year)
business_management_noNo고용보험 사업장관리번호. Omit to use the number stored at login; supply it when the company has more than one workplace.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations only give readOnlyHint=false, destructiveHint=false, openWorldHint=false; the description adds substantial context beyond them: the work24 leg replays a logged-in session, each call consumes one token and creates an XBOSS job whose result is stored, and the call is explicitly declared not purely read-only, which is consistent with readOnlyHint=false. It also discloses that raw verdict states are preserved rather than folded into eligible, the partial/computed_error failure shapes, and the 15-minute download links with 7-day file retention plus the private recovery_receipt rules. The one tension is that the description has the tool reaching live external institutions while openWorldHint=false declares a closed world, though that reads as a fixed set of known sources rather than an outright contradiction.

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?

The purpose, the legs, and the verdict semantics are front-loaded before the failure shapes and file-retention rules, so an agent gets the essentials first. The text is long and runs as a single dense block mixing English and Korean, but nearly every sentence carries operational information an agent needs (partial semantics, receipt handling, token cost). Minor tightening and paragraph breaks would help, but there is little filler.

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?

There is no output schema, so the description carries the full return-value burden and does: it names notices, artifacts[] with download_url, computed, computed_error, partial, pack_run_id, and recovery_receipt, and explains what each means when present. For a multi-leg composite with side effects and file artifacts, nothing an agent needs in order to call it and interpret the result is missing.

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 one of the eight parameters is already documented, and the baseline is 3. The description does add real conditional meaning beyond the schema: supplying notice_field or notice_hashtags turns the optional notices leg into a required one, and it clarifies that no account_link_id is needed because each step resolves its own institution link. It does not add syntax or format detail for the remaining parameters such as application_year or programme_keys.

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

Purpose4/5

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

The first sentence gives a specific verb and resource and decomposes the tool into named legs: the work24 사업주 사전진단 sweep covering every gated 지원사업, plus opendata nts.status, returning which 지원금 the workplace may apply for. An agent can tell this is a composite pack rather than a single-source lookup. It never names a sibling such as work24__subsidy__diagnosis__search to contrast against, so differentiation is implied rather than stated.

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?

Usage conditions are described at the level of individual legs (the notices leg is optional unless notice_field/notice_hashtags are supplied, and then becomes required) and there is a clear follow-up path to xdata__job__result for expired links or receipt-based recovery. What is missing is any statement of when an agent should choose this composite over the single-leg work24 or opendata tools, or when not to call it at all.

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