Skip to main content
Glama

세무 근거 통합검색

search_tax
Read-onlyIdempotent

세무 쟁점의 근거를 한 번에 모으는 통합 그래프 탐색. law 시작 조문에서 위임을 최대 2단계 따라 판례·예규·해석례·참조조문·통칙·부칙 적용근거·별표를 모으고 전문검색으로 보충한다. 결과마다 번호·제목, DB 원문, 시행일·적용버전·미확정 상태와 실제 탐색 경로 요약(graph_route)을, 원문을 싣지 않은 결과는 목차(not_shown)로 반환한다.

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": {
      "search_intents": "<search_intents>"
    },
    "name": "search_tax"
  }
}

Input Schema

NameRequiredDescriptionDefault
as_ofNo선택: YYYY-MM-DD 또는 YYYYMMDD. 조문별 당시 버전을 별도 반환하며 불명 시 현행으로 대체하지 않음.
limitNo한 쪽 건수. 원문 포함(full)은 기본 3·최대 25, 목록(list)은 기본 30·최대 100. 한 쪽의 원문은 합쳐 약 3,000자(앞부분)까지 싣고 나머지는 continuation으로 이어 읽는다
detailNofull = 원문·시행일·적용 상태와 탐색 경로 요약. list = 원문 없이 번호·제목·날짜·요지·길이만. trace = full 에 탐색 경로의 노드·관계 전체와 원천 지문까지full
offsetNo
result_set_idNo다음 페이지는 이전 응답의 식별자를 전달하여 검색 집합 변경을 감지
search_intentsYes유형별 검색 의도. 전체 1~8개. 예: {law:[소득세법 제97조의2],case:[이월과세],ruling:[배우자 증여]}

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / limit / description
      Previous value: -"한 쪽 건수. 원문 포함(full)은 기본 3·최대 25, 목록(list)은 기본 30·최대 100. 한 쪽의 원문은 합쳐 약 16,000자까지 싣고 넘치면 continuation으로 이어 읽는다"New value: +"한 쪽 건수. 원문 포함(full)은 기본 3·최대 25, 목록(list)은 기본 30·최대 100. 한 쪽의 원문은 합쳐 약 3,000자(앞부분)까지 싣고 나머지는 continuation으로 이어 읽는다"
  2. Changed2 schema fields changed
    • changedInput schema / properties / detail / description
      Previous value: -"full = 원문까지. list = 원문 없이 번호·제목·날짜·요지·길이만"New value: +"full = 원문·시행일·적용 상태와 탐색 경로 요약. list = 원문 없이 번호·제목·날짜·요지·길이만. trace = full 에 탐색 경로의 노드·관계 전체와 원천 지문까지"
    • changedInput schema / properties / detail / enum
      Previous value: -[
      -  "full",
      -  "list"
      -]New value: +[
      +  "full",
      +  "list",
      +  "trace"
      +]
  3. Changed1 schema field changed
    • changedInput schema / properties / detail / description
      Previous value: -"full = 원문까지. list = 원문 없이 번호·제목·날짜·요지·길이만(고른 뒤 같은 result_set_id로 offset을 지정하거나 get_evidence로 읽는다)"New value: +"full = 원문까지. list = 원문 없이 번호·제목·날짜·요지·길이만"
  4. Changed4 schema fields changed
    • addedInput schema / properties / detail
      Added value: +{
      +  "default": "full",
      +  "description": "full = 원문까지. list = 원문 없이 번호·제목·날짜·요지·길이만(고른 뒤 같은 result_set_id로 offset을 지정하거나 get_evidence로 읽는다)",
      +  "enum": [
      +    "full",
      +    "list"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / limit / default
      Previous value: -10New value: +3
    • addedInput schema / properties / limit / description
      Added value: +"한 쪽 건수. 원문 포함(full)은 기본 3·최대 25, 목록(list)은 기본 30·최대 100. 한 쪽의 원문은 합쳐 약 16,000자까지 싣고 넘치면 continuation으로 이어 읽는다"
    • changedInput schema / properties / limit / maximum
      Previous value: -25New value: +100
  5. Added

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world). The description adds real behavior beyond that: a hard traversal bound of '최대 2단계' delegation, the exact per-result payload (number, title, DB original, effective date, applied version, unconfirmed status, graph_route summary), and the not_shown table-of-contents substitute when original text is withheld. That is meaningful operational detail, though response-level mechanics like continuation are left to the schema.

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?

Three front-loaded sentences: purpose, traversal mechanism, then returned shape. Dense but each clause carries information, and the mechanism is described before the output contract. Slightly long clauses with heavy punctuation cost it the top score, but there is no 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?

For a 6-parameter tool with a nested required object and an output schema, the description covers the mechanism, traversal depth, and the not_shown fallback so the agent knows what it will get. Because an output schema exists, return-value detail need not be restated. The remaining gap is routing guidance against the many per-type siblings.

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 high (83%), so the schema already documents as_of, limit, detail, offset, result_set_id, and search_intents. The description contributes one useful framing — that 'law' entries act as the delegation anchor traversed up to 2 levels while other types are supplemented by full-text search — but it does not explain how the six type arrays interact or when to populate each, leaving the baseline of 3 appropriate.

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?

States a specific resource and mechanism: integrated graph traversal that starts from a law article and follows delegation up to 2 levels to collect cases, rulings, interpretations, reference articles, general provisions, supplementary bases, and annexes, supplemented by full-text search. This is clearly more than a tautology. It does not explicitly name the per-type siblings (search_cases, search_articles) it generalizes over, so differentiation is inferred rather than stated.

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 phrase '한 번에 모으는' (gather at once) implies this is for broad multi-type evidence gathering, and '전문검색으로 보충한다' hints at a fallback strategy. But there is no explicit statement of when to prefer this over the many per-type search siblings, and no when-not guidance. Usage is implied, not directed.

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.