Skip to main content
Glama

회계위키 근거 묶음

find_evidence
Read-onlyIdempotent

회계 질문 하나에 대해 회계위키의 근거를 한 번에 묶어 반환: 핵심 기준서 문단(앞뒤 문단 요약 포함), 관련 질의회신·감리지적사례(요지와 인용한 기준서 문단), 실무해설. 답변을 쓰기 전 근거 수집용. 질문은 문장 그대로 넣어도 되며, 결과에 '근거 약함' 주의가 붙으면 기준서 용어로 바꿔 다시 호출할 것. 질문자 회사의 적용 기준을 알면 domain 을 지정할 것(상장사 등 K-IFRS: 'ifrs', 비상장 일반기업회계기준: 'kgaap') — 지정하지 않으면 K-IFRS 문단을 중심으로 담고 일반기업회계기준 병행 조항은 따로 표시한다. 각 항목의 id 로 fetch·get_paragraphs 를 부르면 전문을 얻는다. 결과는 이용자 질의에 대한 조회 목적으로만 제공되며 원문 저작권은 제정·발행기관에 있다. 인용 시 응답의 출처 URL 을 표기할 것.

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": {
      "question": "<question>"
    },
    "name": "find_evidence"
  }
}

Input Schema

NameRequiredDescriptionDefault
stdNo기준서 번호로 한정 (예: '1116')
domainNo도메인 한정 — 생략 시 전체
questionYes회계 질문 (예: '임대인이 임대료를 깎아주면 임차인은 어떻게 회계처리하나')
max_charsNo응답 목표 길이(자), 기본 10000

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / domain / enum
      Previous value: -[
      -  "ifrs",
      -  "kgaap",
      -  "audit",
      -  "icfr"
      -]New value: +[
      +  "ifrs",
      +  "kgaap",
      +  "audit",
      +  "icfr",
      +  "law"
      +]
  2. Added

TDQS

A4.6/5.0
Behavior4/5

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

The annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description only needs to add operational behavior — and it does: it discloses that results carry a '근거 약함' weakness flag, that omitting domain changes how K-IFRS versus K-GAAP provisions are presented, and that a citation/attribution obligation attaches to the output. It does not discuss result-size behavior or how max_chars affects the returned bundle, which is the main remaining gap.

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 payload contents, then usage, then follow-up routing, which is the right order for an agent. It is dense rather than padded, though the trailing copyright/attribution sentence is compliance boilerplate that costs a line without affecting tool selection or invocation.

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

Completeness5/5

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

There is no output schema, and for a multi-source research tool the description does the schema's job by describing the shape of the bundle (standard paragraphs plus neighboring summaries, Q&A and audit cases with quoted paragraphs, commentary, per-item ids). Combined with the retry and follow-up-call guidance, an agent has everything needed to invoke it correctly and act on the result.

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?

With schema coverage at 100% the baseline is 3, and the description earns above that by explaining domain semantics (which framework value to pick based on the filer) and by stating that a natural-language question can be passed verbatim. One tension worth flagging: the schema says domain omitted means '전체', while the description says omitted means K-IFRS-centric with K-GAAP parallels marked separately — minor, but it means the default is not fully unambiguous.

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?

States a concrete verb and resource ('회계 질문 하나에 대해 회계위키의 근거를 한 번에 묶어 반환') and then enumerates the returned artifacts: standard paragraphs with surrounding-paragraph summaries, Q&A responses and audit findings with cited paragraphs, and practical commentary. It also distinguishes itself from the retrieval siblings by telling the agent that 'fetch' and 'get_paragraphs' are the follow-up calls for full text, so the boundary is visible without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use ('답변을 쓰기 전 근거 수집용'), an explicit retry rule (if the '근거 약함' warning appears, re-query using standard terminology), and an explicit parameter-selection rule (set domain to 'ifrs' or 'kgaap' when the filer's framework is known). It also names the correct next step after results ('각 항목의 id 로 fetch·get_paragraphs 를 부르면 전문을 얻는다'), which is a full routing chain rather than a vague hint.

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