XBOSS

고용24 기업지원금 작성중 초안 삭제

work24__subsidy__application__delete

Destructive

REQUIRES prior work24__auth__npki_session__login call with same account_link_id. 아직 제출하지 않은 고용24 기업지원금 초안을 삭제합니다. 사용자가 동의한 뒤에만 보내는 confirm 이 필요합니다. 제출한 신청은 삭제가 아니라 withdraw 로 철회합니다. 이 도구는 기관의 기록을 바꿉니다. 첫 호출은 실행되지 않고, 전송할 내용의 미리보기와 1회용 confirmation_token 을 돌려줍니다(오류 WRITE_CONFIRMATION_REQUIRED). 그 미리보기를 사용자에게 그대로 보여 줍니다. 사용자가 동의한 뒤에만 같은 인자에 그 confirmation_token 을 더해 다시 호출합니다. 사용자의 동의 없이 토큰을 넣지 않습니다. 인자를 하나라도 바꾸면 토큰은 무효가 됩니다. 그때는 토큰 없이 호출해 새 미리보기를 받습니다. 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

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "programme_key": "<programme_key>",
      "receipt_no": "<receipt_no>",
      "confirm": "<confirm>"
    },
    "name": "work24__subsidy__application__delete"
  }
}

Input Schema

Name	Required	Description
`confirm`	Yes	되돌릴 수 없는 처리에 대한 명시 확인. true 가 아니면 거부된다.
`receipt_no`	Yes	민원신청접수번호 (cvplRqutRcno). workplace_save 가 발급한 값.
`programme_key`	Yes	카탈로그 사업 키 (예: w24_b0010 고용촉진장려금). subsidy_pack 진단 결과의 programme_key 를 그대로 넣는다.
`account_link_id`	No	연동 ID(UUID v4). 선택 입력입니다. 비워 두면 서버가 API 키로 연동을 찾아 씁니다. 같은 기관에 인증서를 여러 개 연동했을 때만 직접 입력해 주세요. 기관마다 ID 가 다릅니다.
`confirmation_token`	No	첫 호출이 돌려준 1회용 확인 토큰입니다(오류 WRITE_CONFIRMATION_REQUIRED). 같은 인자에 이 값을 그대로 넣어 다시 호출하면 실행됩니다. 10분 뒤 만료되고 한 번만 쓸 수 있습니다.
`business_management_no`	No	11-digit 고용보험 사업장관리번호. 비우면 로그인 시 저장된 값을 쓴다.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 15, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description is fully consistent with them ("이 도구는 기관의 기록을 바꿉니다", "순수 읽기 전용이 아닙니다"). Beyond annotations it discloses the preview/confirm handshake, the WRITE_CONFIRMATION_REQUIRED error on first call, that the first call performs no execution, that token reuse is one-shot, that any argument change invalidates the token, and that an XBOSS job is created per call — behavior an agent cannot infer from the schema.

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 critical constraint (prior login requirement) is front-loaded in capitals and the two-phase flow reads in execution order. There is some redundancy — the "사용자가 동의한 뒤에만" condition is stated twice — and the trailing XBOSS/기관 데이터 변경 sentences are boilerplate that dilute the close.

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?

For a destructive, no-output-schema, six-parameter mutation tool, the description covers authentication, safety gating, error-driven retry, token lifetime, and the destructive/withdraw distinction. An agent has everything needed to call it correctly and safely without consulting other tools' documentation.

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; the description still adds value by explaining the interaction rules the schema does not: the confirmation_token must be added to the same arguments on a retry, any argument change voids the token, and a token-less call regenerates the preview. It also ties confirm to a post-consent step rather than a bare boolean.

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 names a specific verb and object in both languages ("아직 제출하지 않은 고용24 기업지원금 초안을 삭제합니다") and immediately draws the boundary against the sibling tool withdraw ("제출한 신청은 삭제가 아니라 withdraw 로 철회합니다"). An agent can separate delete-draft from withdraw-submitted from the name and first two sentences alone.

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

Usage Guidelines5/5

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

It gives an explicit prerequisite (prior work24__auth__npki_session__login with the same account_link_id), an explicit when-not with the named alternative (submitted applications go to withdraw), and the consent condition for invoking. The two-phase call protocol is spelled out so the agent knows exactly when to make the first and second call.

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

All XBOSS tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?