Skip to main content
Glama
chrisryugj

korean-law-mcp

by chrisryugj
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

get_annexes

Read-onlyIdempotent

Retrieves Korean law annexes, forms, and penalty tables by law name, annex number, or date to find past or current standards, amounts, and criteria.

Instructions

Korean-law-mcp — [별표] 별표/서식 조회. lawName+'별표N'으로 내용 추출. 금액/기준은 별표에 있는 경우 많음. date(기준일)를 주면 그날 시행 중이던 버전의 별표 — 건축허가·착공·처분 시점의 설치기준·과태료표 등 과거 기준이 필요할 때(제명이 바뀐 법령도 옛 버전까지, 별표 번호가 시점마다 달라 query로 별표명을 주는 편이 안전).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
joNo위임 조문 (예: '제38조', '38'). 조문 동반 질의('관세법 제38조 별표2')의 조문 맥락 — 별표명의 '(제38조 관련)' 표기와 대조해 좁히고, 응답에 위임 관계를 표기
kndNo1=별표, 2=서식, 3=부칙별표, 4=부칙서식, 5=전체
dateNo기준일 (예: '2015-06-01'). 지정 시 그날 시행 중이던 법령 버전의 별표를 조회 — 건축허가·착공·처분·위반 시점 기준이 필요할 때. 제명이 바뀐 법령도 옛 버전까지 찾는다. 별표 번호는 시점마다 다를 수 있으니 query(별표명)로 좁히는 것이 안전. 미지정 시 현행
queryNo별표명으로 좁히기 (예: '운전면허 취소·정지', '과태료'). 번호를 모를 때 사용. 1건으로 좁혀지면 그 별표 본문을 바로 추출
bylSeqNo별표번호 (예: '000300'). 지정 시 해당 별표 파일을 다운로드하여 텍스트로 추출
annexNoNo별표 번호 (예: '4', '별표4', '제4호'). bylSeq 대체 입력
lawNameYes법령명 (예: '관세법'). 별표를 바로 지정하려면 '... 별표4' 또는 '... 별표1의2'처럼 함께 입력 가능

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv4.15.5
    • addedInput schema / properties / date
      Added value: +{
+  "description": "기준일 (예: '2015-06-01'). 지정 시 그날 시행 중이던 법령 버전의 별표를 조회 — 건축허가·착공·처분·위반 시점 기준이 필요할 때. 제명이 바뀐 법령도 옛 버전까지 찾는다. 별표 번호는 시점마다 다를 수 있으니 query(별표명)로 좁히는 것이 안전. 미지정 시 현행",
+  "type": "string"
+}
  2. Changed2 schema fields changedv4.12.0
    • addedInput schema / properties / jo
      Added value: +{
+  "description": "위임 조문 (예: '제38조', '38'). 조문 동반 질의('관세법 제38조 별표2')의 조문 맥락 — 별표명의 '(제38조 관련)' 표기와 대조해 좁히고, 응답에 위임 관계를 표기",
+  "type": "string"
+}
    • addedInput schema / properties / query
      Added value: +{
+  "description": "별표명으로 좁히기 (예: '운전면허 취소·정지', '과태료'). 번호를 모를 때 사용. 1건으로 좁혀지면 그 별표 본문을 바로 추출",
+  "type": "string"
+}
  3. Addedv4.9.1
  4. Removedv4.9.1
  5. First observedv4.4.2

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so safety is covered. The description adds non-obvious behavior beyond them: unspecified date means the currently-in-force version, a specified date reaches back to renamed/superseded laws, and a single query match returns the annex body directly. It omits return-size/pagination and rate-limit context, keeping it at a 4.

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 definition is front-loaded — resource identification opens, then parameter behavior — with no filler sentences. It is dense with parentheticals and mid-sentence dashes that make it slower to parse, but each clause carries semantic content rather than repetition.

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 7-parameter tool with one required argument and no output schema, the description covers the critical defaults (현행 vs historic via date), the numbering-shift caveat, and the narrowing-by-name path. It does not explicitly describe output form (download vs extracted text beyond the bylSeq schema note), so it is strong but not exhaustive.

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 100%, so every parameter is already documented and the baseline is 3. The description mostly restates the schema's date semantics and adds only one cross-parameter recommendation (narrowing by query name is safer than by number because numbering shifts across versions). Useful but marginal beyond the schema.

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 resource and verb — '[별표] 별표/서식 조회' and 'lawName+별표N으로 내용 추출' — so an agent knows this retrieves annex/form content rather than main law text. It also adds scope color ('금액/기준은 별표에 있는 경우 많음'). It does not, however, explicitly name a sibling such as get_law_text to contrast against, so 5 is not warranted.

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

Usage Guidelines4/5

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

It gives clear conditional guidance: pass date when you need the version in force at a past point (건축허가·착공·처분 시점) and use query when the 별표 number is unknown or has shifted over time. That is actionable when-to-use context. It stops short of stating when NOT to use the tool or pointing to a specific alternative sibling, so it is a 4 rather than a 5.

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