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

korean-tax-calc-mcp

ksic_lookup

Read-onlyIdempotent

Look up Korean Standard Industrial Classification (KSIC) codes by industry name or code, and convert 10th-edition codes to 11th-edition for accurate tax-industry matching.

Instructions

Korean Standard Industrial Classification (KSIC) code lookup by name or code (한국표준산업분류 코드 찾기). 한국표준산업분류(11차, 통계청 고시 제2024-203호) 코드 찾기 — 업종 이름으로 코드를, 코드로 이름·상위 단계·하위 세세분류를 찾고, 10차 코드는 11차로 연계한다. 언제: kr_comparable_candidates에 넣을 업종 코드를 정하기 전(기억으로 넣지 말고 여기서 확인 — 예: 화장품 도매는 46443, 46444는 비누·세정제 도매), 후보의 등록 코드가 짧을 때(예: '204') 그 아래 세세분류가 무엇인지 볼 때, 옛 보고서의 10차 코드를 11차로 바꿀 때. 입력: query → 업종 이름 낱말(띄어쓰기로 여러 낱말, 모두 들어간 항목) 또는 코드(대분류 문자 AU, 숫자 25자리), level → 이름 검색을 한 단계로 좁힘(선택). 결과: 이름 검색 → 맞는 항목(세세분류부터), 코드 → 이름·단계·상위·하위 세세분류(10차 코드면 11차 코드). OpenDART 기업개황 업종 코드는 11차. 근거·범위: 분류표·구·신 연계표는 고시 해설서 원문에서 뽑아 단계별 항목 수를 고시 표와 대조함. 어느 업종이 비교대상으로 적절한지는 판단하지 않음.

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": {
      "query": "<query>"
    },
    "name": "ksic_lookup"
  }
}

Input Schema

NameRequiredDescriptionDefault
levelNo이름 검색 단계 좁히기(선택)
queryYes업종 이름 낱말(예 '화장품', '화장품 도매') 또는 코드(예 '2042', '46443', 'C')

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.67.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real behavior beyond them: results differ by input mode (name search returns matches starting at 세세분류; code lookup returns name, level, parent and child 세세분류, plus the 11차 equivalent for 10차 input), and it discloses data provenance (extracted from the 고시 해설서 and item counts cross-checked against the official table). It stops short of describing no-match or ambiguous-match behavior, so not a 5.

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 a one-line purpose in both Korean and English, then cleanly sectioned (언제 / 입력 / 결과 / 근거·범위), so an agent can scan rather than parse prose. The bilingual opening is mildly redundant and the '언제' line is dense, but no sentence is filler.

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?

With only two parameters, no output schema, and annotations already covering the safety profile, the description supplies what structured fields cannot: version/authority of the classification, the 10차→11차 conversion behavior, and the limit of its judgment. Minor gaps remain (empty-result and multiple-match handling), but nothing needed to call it correctly is missing.

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 baseline would be 3, but the description adds semantics the schema does not: multi-word name queries are AND-matched ('띄어쓰기로 여러 낱말, 모두 들어간 항목') and the code form is constrained to 대분류 letters A–U or 2–5 digits. The `level` parameter's role as a narrowing filter for name search is also clarified.

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+resource (KSIC code lookup by name or code) and pins the reference edition (11차, 통계청 고시 제2024-203호). It also draws an explicit boundary against a related tool by saying it does not judge whether an industry is a suitable comparison target, which is a genuine scope statement rather than a restatement of the name.

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?

The '언제' block gives three concrete triggering situations: before selecting a code for kr_comparable_candidates (with an explicit 'don't enter from memory, verify here' instruction and a worked example), when a candidate's registered code is too short to see its 세세분류, and when converting 10차 codes from old reports. It names the alternative (memory/guessing, and the companion candidate tool) and the condition that routes to this tool.

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