Skip to main content
Glama
korean-tax-calc-mcp

korean-tax-calc-mcp

find_tool

Read-onlyIdempotent

Finds the right Korean tax calculator from a plain-language query and returns candidate tools with usage guidance. Use it before concluding that no calculator exists.

Instructions

Tool finder: find the right tool among Korean tax calculators (계산 도구 찾기). 맞는 계산 도구 찾기 — 도구가 많으니, 어떤 도구를 쓸지 모르겠으면 먼저 이걸 부른다. 언제: 계산 문제를 받았는데 맞는 도구 이름이 바로 떠오르지 않을 때, 또는 '이 계산 도구는 없다'고 판단하기 전에 반드시. 입력: 찾는 계산 → query(평소 말, 세목·쟁점·조문 무엇이든), 개수 → n. 결과: 후보 도구 목록(이름·한 줄 설명·언제 쓰는지·일치 이유). 후보가 없으면 계산 도구가 없는 것이니 korean-tax-mcp로 조문을 찾는다. 엑셀·스프레드시트·계산 근거(excel·xlsx·workings)를 찾는 말이면 결과에 '엑셀 문서' 한 줄 — 직접 짠 뒤 verify_workbook으로 대조(법정서식 엑셀은 export_workbook). 메모·의견서·Word(docx) 문서를 찾는 말이면 결과에 '메모 문서' 한 줄 — korean-tax-mcp tax_memo_guide → build_tax_memo(이 서버는 메모를 만들지 않음).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "find_tool"
  }
}

Input Schema

NameRequiredDescriptionDefault
nNo돌려줄 도구 수(1~10)
queryNo찾는 계산을 평소 말로. 예: '아파트 팔았을 때 양도세', '보험차익으로 산 기계', '접대비 한도', '해산한 법인 청산소득'
keywordNoquery와 같음(korean-tax-mcp find_article과 같은 이름으로 불러도 되게)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.15.1

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is low, yet the description still discloses the return shape (name, one-line summary, when-to-use, match reason) and the empty-result behavior (means no such calculator exists). It further explains that certain query types inject a special one-line hint into the results and that this server does not create memos — behavior an agent could not infer from annotations.

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?

The 언제/입력/결과 structure is front-loaded and scannable, and the fallback routing is worth its space. It runs long with several branching sentences, but no sentence is filler given the routing role.

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?

With no output schema, the description carries the burden of describing results, and it does so concretely including the empty-candidate case. For a 3-parameter, zero-required router this covers everything an agent needs to call it correctly and interpret what comes back.

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; the description adds meaning by saying query accepts everyday phrasing and may be a tax item, issue, or statutory article, which broadens the agent's sense of valid inputs. It does not mention the keyword alias that the schema documents as interchangeable with query, so it stops short of full coverage.

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 specific verb and resource — 'Tool finder: find the right tool among Korean tax calculators' — and makes clear it is a router that returns candidate calculators rather than a calculator itself. That framing lets an agent separate it from the many sibling calculation tools 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 triggers: when the correct tool name doesn't come to mind, and mandatorily before concluding a calculator does not exist. It also routes downstream: no candidates → look up articles in korean-tax-mcp; excel/xlsx queries → verify_workbook or export_workbook; memo/docx → tax_memo_guide then build_tax_memo.

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

Deploy Server

Other Tools