Skip to main content
Glama

급여명세서 엑셀 생성

payroll_artifact__payslip_xlsx

attribution_ym, payment_date, employees[] 로 직원마다 시트 하나인 급여명세서 엑셀(xlsx) 한 개를 만듭니다. 우리 플랫폼 키로만 돌아 account_link_id 가 필요 없습니다. 결과는 data 의 요약(attribution_ym, employee_count)과 artifacts[] 의 엑셀 한 개(서명된 download_url)입니다. 조합 병합 결과가 아니고 메일로 보내지도 않습니다. 파일: 엑셀(xlsx) · 이 작업의 결과로 만든 문서. 결과의 artifacts[] 에 실리고, 내려받기 링크(download_url)는 15분 동안 열리며 파일은 7일 동안 보관됩니다. 링크가 만료되면 결과의 job_id 로 xdata__job__result 를 다시 불러 새 링크를 받습니다. 로그인 없이 받은 결과는 함께 온 recovery_receipt 를 따로 보관했다가, 처음의 job_id 나 pack_run_id 와 함께 xdata__job__result 에 보내세요. 증표로는 그 결과 하나만, 원래 파일 보관 기간이 끝날 때까지 열 수 있습니다. 증표는 공개하지 마세요. 잃어버리면 가입해도 되찾을 수 없습니다. 나중에 로그인해도 증표는 그대로 쓰이고, 다른 결과는 열지 못합니다. 증표가 없으면 처음 계정과 같은 환경(데모 · 정식)에서만 결과를 읽을 수 있습니다. For an authenticated call, generate and save request_idempotency_key before the first request. Reuse it with the same arguments only to recover that request after a lost response; use a new key for a new execution. Without it, calling again remains a new request. This optional key is not available to anonymous taste calls. Keep any provider-specific idempotency_key unchanged; it is a different field. 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": {
      "attribution_ym": "<attribution_ym>",
      "payment_date": "<payment_date>",
      "employees": "<employees>",
      "workplace_name": "<workplace_name>",
      "business_registration_no": "<business_registration_no>",
      "workplace_address": "<workplace_address>"
    },
    "name": "payroll_artifact__payslip_xlsx"
  }
}

Input Schema

NameRequiredDescriptionDefault
employeesYesEmployee rows for payslip sheets (amounts already computed).
company_nameNoAlias for workplace_name (runtime accepts either).
payment_dateYesPayment date YYYY-MM-DD.
attribution_ymYesPayroll attribution month as YYYYMM (e.g. 202603).
workplace_nameYesWorkplace / company display name (required for payslip).
workplace_addressYes
request_idempotency_keyNoOptional same-request recovery key for authenticated calls; see the tool description.
business_registration_noYes

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 declare readOnlyHint=false, destructiveHint=false, openWorldHint=false; the description goes well beyond them by disclosing that each call creates an XBOSS job and persists its result, costs one token, is not purely a read despite reading institution originals, and that download links live 15 minutes while files persist 7 days. It also explains the recovery_receipt flow and the consequence of losing it. Some of this is generic boilerplate rather than tool-specific, which keeps it from a 5, but it is consistent with the non-read-only annotation.

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 purpose is front-loaded, but the text is long, mixes Korean and English mid-paragraph, and repeats output/recovery details in near-duplicate clauses. The idempotency paragraph restates guidance that the schema description also points to, so not every sentence earns its place.

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 tool with 8 parameters, 6 required, and no output schema, the description supplies the missing return shape (data summary with attribution_ym and employee_count, artifacts[] with signed download_url) plus retention and recovery behavior. That covers what an agent needs to call it and handle the result, with only the nested employee payload left entirely to the schema.

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 75%, so the nested employee row fields and format constraints are already documented in the schema. The description reinforces attribution_ym, payment_date, employees[] and clarifies that account_link_id is not needed, but adds no new syntax or validation meaning beyond what the schema states. Baseline 3 applies where the schema carries most of the weight.

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 opens with a concrete verb and artifact: it creates a single xlsx payslip workbook with one sheet per employee, parameterized by attribution_ym, payment_date and employees[]. It also explicitly negates two confusable behaviors (not a combination-merge result, not emailed), which lets an agent separate it from siblings such as register_xlsx without opening a schema.

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?

It gives useful operating context — runs on the platform key, so account_link_id is unnecessary — and prescribes the recovery path via xdata__job__result for expired links and the request_idempotency_key reuse rules. However, it never states when to choose this over the sibling artifact/registration tools, and no exclusion or alternative is named for ordinary use.

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