XBOSS

홈택스 원천세 기한후신고 기본정보 저장

hometax__tax__withholding__late_report__basic_save

Destructive

REQUIRES prior hometax__session__login call with same account_link_id. 원천세 기한후신고서의 신고 구분과 납세자 정보를 작성 중인 신고서에 저장합니다. 제출하지 않습니다. 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": {
      "source_job_id": "<source_job_id>",
      "expected_snapshot_hash": "<expected_snapshot_hash>"
    },
    "name": "hometax__tax__withholding__late_report__basic_save"
  }
}

Input Schema

Name	Required	Description
`source_job_id`	Yes	이어서 진행할 이전 단계 작업의 job_id 를 그대로 입력합니다(job_ 으로 시작하는 작업 번호). 작성 준비(init)나 기본정보 저장(basic_save) 결과, 또는 그 상태에서 실행한 조회(lookup) 결과를 받습니다. 같은 조직과 환경, 같은 기관 연결에서 이 신고 유형으로 성공한 작업이어야 하고 아니면 진행하지 않고 거절하며, 받지 않는 작성 상태의 결과이면 409 로 거절합니다.
`basic_document`	No	기관에서 불러온 기본정보 중 바꿀 값만 입력합니다. 생략한 값은 유지합니다.
`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.
`expected_snapshot_hash`	Yes	source_job_id 작업 결과의 snapshot_hash 를 그대로 입력합니다(소문자 16진수 64자리). 그 작업의 내용과 맞지 않으면 진행하지 않고 작성 내용이 바뀌었다는 오류(409)로 거절합니다.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 15, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the mutation profile is known; the description adds genuinely new behavior: one token consumed per call, an XBOSS job created and result persisted, and an explicit warning that the call is not pure read-only regardless of whether the agency original is only being read. It does not say what existing draft state is overwritten or what a failed save leaves behind, and the closing line about '기관 데이터 변경은 도구별 실행 내용과 기존 확인 절차' is generic rather than concrete.

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-loaded with the session prerequisite, then purpose, then cost and side effects, which is the right order for an agent scanning for blockers. The trailing sentence about agency data changes and existing confirmation procedures is vague boilerplate that could be dropped without losing information.

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

Completeness4/5

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

For a 4-parameter mutation tool with no output schema, the definition covers prerequisite, non-submission boundary, per-call cost, and side effects, while the fully-described schema carries parameter and conflict semantics. What is missing is what the tool returns on success and how the draft is affected beyond the patch, but that gap is modest given annotation and schema coverage.

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 source_job_id chaining rules, snapshot-hash matching, partial-patch semantics, and account_link_id fallback are all already documented in the schema. The description text adds no parameter-level meaning of its own, making the baseline 3 correct here.

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?

Names a specific verb (저장합니다) and resource (원천세 기한후신고서의 신고 구분과 납세자 정보) and scopes it to the in-progress draft. The sentence '제출하지 않습니다' explicitly separates it from the submit sibling, so an agent can tell save from submit without opening either 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?

States a hard prerequisite ('REQUIRES prior hometax__session__login call with same account_link_id') and a negative boundary (does not submit). It does not say where this step sits relative to init, annex_save, detail_save, preview, or which of those an agent should pick instead, but the surrounding context is clear enough to act on.

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?