Skip to main content
Glama

verify_statement

Read-onlyIdempotent

Checks a statement or claim word by word against Korean statute text, returning contradiction signals, differing phrases, and missing provisos for citation review.

Instructions

Check one statement against the statute text word by word. 진술·주장을 조문 원문과 글자 수준에서 대조해 모순 신호(숫자·양태·반대말·시점)와 단서 누락을 돌려준다.

언제: 보기 문장·주장·고객 진술이 특정 조문과 맞는지 확인할 때. 조문을 읽고도 놓치는 차이를 표로 보여 준다 — 법적 판단을 대신하지 않는다. 반환: {법령, 조, 시행본, 판정('모순'|'구절 다름'|'차이 없음'|'판단 필요'), 근거:{위치, 원문}, 대조:[{종류,진술,조문}], 단서:[...], 겹침, 주의}.

  • 판정: 숫자·양태·반대말·시점 신호 하나라도 있으면 '모순', 신호는 없지만 진술과 원문 구절이 다르면 '구절 다름'(대조에 진술·조문 구절을 원문 그대로 — 같은 뜻인지는 직접 판단), 다른 구절도 없고 겹침 0.5 이상 '차이 없음', 겹침 0.5 미만 '판단 필요'. 읽기 전용. 법제처 API 필요(LAW_OC). 조문 문구는 시행본 원문 그대로 — 지어내지 않는다.

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": {
      "statement": "<statement>",
      "law_name": "<law_name>",
      "article": "<article>"
    },
    "name": "verify_statement"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoOutput language. 'en': English keys and labels, official English texts where available (tax treaties, statutes), other Korean texts returned with a host_ai_translate instruction (your AI translates); Solar machine translation only when UPSTAGE_API_KEY or on-prem Solar is configured. 기본 'ko'ko
as_ofNo기준일 YYYYMMDD. 생략하면 오늘
articleYes조문 번호. '제112조' 또는 '제21조' 형식
law_nameYes정식 법령명. 예: '국세징수법', '소득세법', '법인세법', '국세기본법'
paragraphNo특정 항만 대조. '제2항'·'2' 등. 주면 그 항·하위 단위만 대조
statementYes대조할 진술·한 문장·주장. 예: '관할 세무서장은 체납자가 2회 체납하고 체납액이 2천만원인 경우 사업의 정지 또는 허가등의 취소를 요구할 수 있다.'

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.12.10
    • changedInput schema / properties / paragraph / description
      Previous value: -"특정 항만 대조. '②'·'제2항'·'2' 등. 주면 그 항·하위 단위만 대조"New value: +"특정 항만 대조. '제2항'·'2' 등. 주면 그 항·하위 단위만 대조"
  2. Addedv0.9.1

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so safety is covered structurally. The description still adds real value beyond them: it discloses the external dependency ('법제처 API 필요(LAW_OC)'), states that article text is quoted verbatim from the in-force version and never fabricated, and spells out the verdict decision rules including the 0.5 overlap threshold. What it omits is failure behavior — what happens when the law name or article is not found, or when the API is unavailable.

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 description is front-loaded: purpose first, then when-to-use, then return shape, then constraints. The return-shape block is dense but earns its place because no output schema exists. Minor waste in the redundant bilingual restatement of the opening sentence.

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?

There is no output schema, so the description correctly takes on the return contract, enumerating keys (법령, 조, 시행본, 판정, 근거, 대조, 단서, 겹침, 주의) and defining each verdict category with thresholds. That is substantially complete for a read-only comparison tool. It falls short only on error and empty-result paths, which an agent would need when the requested law or article does not resolve.

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 all six parameters, including the lang enum behavior and as_of default, are already documented in the schema. The description adds comparison semantics at the statement level ('글자 수준에서 대조') and notes that paragraph limits the comparison scope to one paragraph, but supplies no format or edge-case guidance beyond that. With the schema carrying the parameter burden, the baseline 3 is 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?

The first sentence states a concrete verb and resource: check one statement against statute text word by word, returning contradiction signals and omitted provisos. It clearly scopes the tool to textual comparison and disclaims legal judgment ('법적 판단을 대신하지 않는다'), which separates it from advisory siblings. It never names a sibling such as verify_citations or compare_with_case, so the agent must infer the boundary itself.

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?

The '언제' line gives an explicit trigger: when a quoted sentence, claim, or client statement must be checked against a specific article, and it notes the tool surfaces differences you miss even after reading the article. There is no when-not guidance and no named alternative for cases where the agent wants case law comparison or citation validation instead.

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