Skip to main content
Glama

지방소득세 특별징수 신고 명세 저장

wetax__tax__local_income__special_withholding__statement_save
Destructive

먼저 호출할 도구: wetax__session__login (같은 account_link_id). 기관에 저장합니다. 소득자별 명세 줄을 검사한 뒤 저장합니다. 명세는 선택이라 줄 없이 보내면 명세 없이 다음 단계로 넘어갑니다. 소득 종류, 성명, 식별번호가 같은 줄이 둘이면 거절합니다. 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": {
      "dclr_id": "<dclr_id>"
    },
    "name": "wetax__tax__local_income__special_withholding__statement_save"
  }
}

Input Schema

NameRequiredDescriptionDefault
dclr_idYes신고 식별자입니다. 신고인 저장이 돌려준 값을 그대로 넣습니다.
statement_rowsNo소득자별로 한 줄씩 넣는 목록입니다. 명세는 선택이라 줄을 하나도 보내지 않으면 명세 없이 다음 단계로 넘어갑니다. 줄을 보낼 때는 소득 종류 코드(income_type_code), 지급일(payment_date), 소득자 성명(payee_name), 소득자 식별번호(payee_identifier), 과세표준(tax_base_amount), 산출세액(calculated_tax_amount), 조정 환급액(adjustment_amount), 납부액(payment_amount)을 보내고, 모든 줄의 과세표준 합계와 산출세액 합계가 저장된 신고의 합계와 같아야 합니다. 소득 종류와 성명, 식별번호가 모두 같은 줄을 두 번 넣지 않습니다.
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.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / dclr_id / description
      Previous value: -"Draft filing ID returned by the declarant step."New value: +"신고 식별자입니다. 신고인 저장이 돌려준 값을 그대로 넣습니다."
    • changedInput schema / properties / statement_rows / description
      Previous value: -"One row per payee: income_type_code, payment_date, payee_name, payee_identifier, tax_base_amount, calculated_tax_amount, adjustment_amount, payment_amount."New value: +"소득자별로 한 줄씩 넣는 목록입니다. 명세는 선택이라 줄을 하나도 보내지 않으면 명세 없이 다음 단계로 넘어갑니다. 줄을 보낼 때는 소득 종류 코드(income_type_code), 지급일(payment_date), 소득자 성명(payee_name), 소득자 식별번호(payee_identifier), 과세표준(tax_base_amount), 산출세액(calculated_tax_amount), 조정 환급액(adjustment_amount), 납부액(payment_amount)을 보내고, 모든 줄의 과세표준 합계와 산출세액 합계가 저장된 신고의 합계와 같아야 합니다. 소득 종류와 성명, 식별번호가 모두 같은 줄을 두 번 넣지 않습니다."
  2. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations mark this as a mutating, destructive operation, and the description is consistent with that ('이 호출은 순수 읽기 전용이 아닙니다'). Beyond the annotations, it discloses that the call creates an XBOSS job, persists the processing result, and rejects duplicate payee rows; what it does not clarify is whether a partial save is rolled back when validation fails.

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?

The opening prerequisite and the save action are front-loaded, which is good, but the tail contains generic boilerplate about XBOSS jobs, original-record lookups, and '기관 데이터 변경은 도구별 실행 내용과 기존 확인 절차를 따릅니다' that adds no actionable information. The optionality and validation rules are buried in the middle instead of grouped.

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?

There is no output schema, and the description covers the key things an agent needs: prerequisite login, optional rows, validation rules, and that the operation advances the workflow. It would be stronger if it said what value (e.g., a returnable identifier or status) the save produces for subsequent steps.

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 the schema already documents all three parameters, including the statement row fields and the account_link_id fallback behavior. The description restates the key business rule that tax-base and calculated-tax totals must match the saved return and that duplicate income-type/name/identifier rows are rejected, but adds little beyond what the schema text already provides.

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 description names a specific verb and resource: it saves per-payee statement rows of a special withholding return to the agency ('소득자별 명세 줄을 검사한 뒤 저장합니다'). It does not, however, distinguish this tool from closely named siblings such as adjustment_save or declarant_save, so an agent must infer the ordering of the workflow from the '다음 단계' wording.

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?

The definition gives a clear precondition (call wetax__session__login first with the same account_link_id) and a clear conditional branch: the statement is optional, and if no rows are sent the call advances without a statement. It does not state when to prefer this tool over sibling save tools, but the workflow context is otherwise explicit.

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