Skip to main content
Glama
Sign In

XBOSS

by kr.xdata
OverviewDiscussionsAdmin

신고서 본문 조회

hometax__tax__vat__draft__load

REQUIRES prior hometax__session__login call with same account_link_id. 부가가치세 정기신고에서 신고서 본문 조회 작업을 수행합니다. 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": {
      "business_no": "<business_no>",
      "year": "<year>",
      "half": "<half>"
    },
    "name": "hometax__tax__vat__draft__load"
  }
}

Input Schema

NameRequiredDescriptionDefault
halfYes과세 기수입니다. 1 은 1기(1월부터 6월), 2 는 2기(7월부터 12월)입니다.
yearYes불러올 신고의 과세 연도입니다. 네 자리 정수로 입력합니다.
procedureNo신고 절차입니다. REGULAR 는 정기신고, AMENDMENT 는 수정신고이고 입력하지 않으면 REGULAR 입니다. AMENDMENT 이면 original_receipt_job_id, source_job_id, expected_snapshot_hash 를 함께 입력해야 합니다.REGULAR
business_noYes신고서를 불러올 사업자의 사업자등록번호입니다. 하이픈 없이 숫자 10자리로 입력합니다.
period_kindNo신고 구분입니다. PRELIMINARY 는 예정신고(기수의 앞 석 달), FINAL 은 확정신고(기수 여섯 달)이고 입력하지 않으면 PRELIMINARY 입니다. 정기신고(procedure 가 REGULAR)는 PRELIMINARY 만 받습니다.PRELIMINARY
preparationNo부가세 준비 사건에서 받은 참조가 있을 때만 입력합니다. 입력하지 않아도 신고서를 불러올 수 있습니다. 부가세 준비 사건에서 승인된 신고 자료를 이 신고서에 잇는 참조 객체이고 case_id, case_revision, company_id, package_ref, approval_ref, package_input_hash, inventory_hash 를 담습니다. source_policy 와 함께 입력하면 거절합니다.
source_job_idNo수정신고를 불러올 때만 입력합니다. 수정신고 생성 결과나 그 수정신고를 앞서 불러온 결과의 job_id 입니다. 정기신고에 입력하면 거절합니다.
source_policyNo부가세 준비 사건에서 받은 참조가 있을 때만 입력합니다. 입력하지 않아도 신고서를 불러올 수 있습니다. 고객이 이미 채택한 원천 자료 정책을 이 신고서에 잇는 참조 객체이고 case_id 와 company_id 를 담습니다. preparation 과 함께 입력하면 거절합니다.
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.
expected_snapshot_hashNosource_job_id 와 함께 입력합니다. 그 작업 결과의 snapshot_hash 입니다(16진수 64자리).
original_receipt_job_idNo수정신고(procedure 가 AMENDMENT)를 불러올 때만 입력합니다. 수정할 당초 신고의 접수 작업 job_id 입니다. 정기신고에 입력하면 거절합니다.
request_idempotency_keyNoOptional same-request recovery key for authenticated calls; see the tool description.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false and destructiveHint=false, but the description adds genuinely non-obvious context: each call consumes a token ('호출마다 토큰 1소진'), creates an XBOSS job and stores results, and explicitly warns '이 호출은 순수 읽기 전용이 아닙니다' despite it being a lookup. That disclosure goes beyond what the annotations convey; minor deduction for some idempotency boilerplate that repeats the schema field.

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 prerequisite is correctly front-loaded, but the body drifts between English and Korean and spends several sentences on idempotency and provider-key boilerplate before returning to the actual behavior. Structurally sound, but not tight.

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

Completeness3/5

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

For a 12-parameter tool with no output schema, the description covers authentication, side effects, and idempotency well, but says nothing about what the loaded return body looks like or how the procedure/amendment parameters interact at runtime. An agent knows how to call it and what it costs, but not what it returns.

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, but the description adds real meaning about request_idempotency_key semantics (recovery-only reuse, distinct from provider-side idempotency_key) that the schema field defers to with 'see the tool description.' The remaining parameters are left entirely to their schema descriptions, so it does not fully compensate.

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 ('부가가치세 정기신고에서 신고서 본문 조회 작업을 수행합니다' – load the VAT return body for a regular filing), which an agent can map to the LOAD action in the schema. It does not, however, contrast itself with plausible siblings such as the VAT return history search or amendment tools, leaving differentiation to the schema's fixed-operation marker.

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?

The prerequisite is stated clearly and up front ('REQUIRES prior hometax__session__login call with same account_link_id'), and the idempotency-key usage rules (reuse only to recover a lost response, new key for a new execution) are spelled out. What is missing is any when-to-use guidance relative to alternatives — nothing says when to load a draft versus searching history or creating an amendment.

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

All XBOSS toolsInspect
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