Skip to main content
Glama

홈택스 원천세 신고 접수 내역 조회

hometax__tax__withholding__regular_report__history

먼저 호출할 도구: hometax__session__login (같은 account_link_id). 기간을 정해 접수된 원천세 신고(정기신고, 수정신고, 기한후신고) 목록을 조회합니다. 행마다 접수번호, 접수일, 신고일, 귀속연월, 지급연월, 신고 구분, 납부세액, 납부 상태를 돌려주고 page 에 페이지 번호와 전체 건수를 싣습니다. start_date 와 end_date 는 신고일 기준 YYYYMMDD 이고 page_size 는 최대 100 입니다. 조회만 하고 기관에 아무것도 바꾸지 않습니다. 정기신고를 제출한 뒤 접수됐는지 확인할 때 부르세요. 로그인한 호출이면 첫 요청 전에 request_idempotency_key 값을 만들어 저장하세요. 응답을 받지 못한 그 요청을 되찾을 때만 같은 인자와 함께 그 값을 다시 보내고, 새로 실행할 때는 새 값을 쓰세요. 이 값 없이 다시 부르면 새 요청이 됩니다. 계정 없이 맛보기로 부를 때는 이 선택 칸을 쓸 수 없습니다. 기관 업무에 따로 있는 idempotency_key 칸은 다른 칸이니 그대로 두세요. 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": {
      "business_no": "<business_no>",
      "start_date": "<start_date>",
      "end_date": "<end_date>"
    },
    "name": "hometax__tax__withholding__regular_report__history"
  }
}

Input Schema

NameRequiredDescriptionDefault
end_dateYes조회 종료일(신고일 기준, YYYYMMDD). 시작일보다 앞설 수 없습니다.
page_numNo페이지 번호(1부터, 기본 1)
page_sizeNo페이지 크기(한 페이지의 행 수, 1부터 100까지, 기본 10)
start_dateYes조회 시작일(신고일 기준, YYYYMMDD)
business_noYes원천징수의무자 사업자등록번호 10자리(숫자만)
account_link_idNo연동 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.
request_idempotency_keyNo로그인한 호출에서 응답을 못 받은 같은 요청을 되찾을 때 쓰는 선택 값입니다. 쓰는 법은 도구 설명에 있습니다.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / request_idempotency_key / description
      Previous value: -"Optional same-request recovery key for authenticated calls; see the tool description."New value: +"로그인한 호출에서 응답을 못 받은 같은 요청을 되찾을 때 쓰는 선택 값입니다. 쓰는 법은 도구 설명에 있습니다."
  2. First observed

TDQS

A4/5.0
Behavior5/5

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

Goes well beyond the annotations: it discloses a 1-token cost per call, that an XBOSS task is created and its result persisted, and explicitly reconciles the apparent paradox that it does not modify agency data yet is not purely read-only (matching readOnlyHint=false). It also spells out idempotency semantics — reuse the key only to recover an unanswered request, use a fresh key for a new execution, and do not confuse it with the agency-level idempotency_key parameter.

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

Conciseness3/5

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

Purpose, return fields, and parameter semantics come early, but the tail is a run-on block of policy boilerplate (token accounting, XBOSS task creation, agency-procedure caveats) with at least one garbled clause ('호출마다 토큰 1소진 요청 처리 시 XBOSS 작업을 생성하고'). It is denser than it needs to be for a paginated read tool.

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?

With no output schema, the description compensates by listing every returned column plus the page envelope (page number and total count), and the annotations' safety profile is fully explained. The missing piece is the relationship to the sibling amendment/late history tools, which an agent would likely need before picking this one.

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 coverage is 100%, so date formats, the YYYYMMDD basis, page_size maximum, and account_link_id fallback are already documented in the schema, and the description largely repeats them. The one addition of real value is the operational meaning of request_idempotency_key (retry versus new execution), which the schema defers to the description for. That lifts it only slightly above the baseline-3 placeholder.

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?

States a specific verb and resource: querying a list of accepted withholding tax filings (regular, amended, late) for a date range, and enumerates the returned row fields. It is clearly distinguishable from mutation siblings like submit or preview, but it does not distinguish itself from amendment_report__history or late_report__history even though it claims to cover the same amended/late filing types, leaving a real scope overlap unresolved.

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?

Gives an explicit prerequisite (call hometax__session__login first with the same account_link_id) and an explicit trigger (call this after submitting a regular report to confirm acceptance). It also warns that the optional idempotency field is unavailable for account-less trial calls. What it never states is when to choose this tool over the amendment/late history siblings, which would be the one genuinely useful exclusion here.

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