Skip to main content
Glama

casebook_search

Read-onlyIdempotent

Search the NTS 2025 Tax Interpretation Casebook's 96 curated cases by issue or keyword to find representative Korean tax interpretations.

Instructions

Search the NTS 2025 Tax Interpretation Casebook (96 curated cases). 국세청 「2025 세법해석 사례집」 쟁점 검색. 언제: 국세청이 대표 사례로 고른 해석을 빠르게 볼 때(오프라인, 즉시). 최신·전체 해석은 search_tax_rulings. 반환: {결과: [{문서번호, 회신일, 분야, 쟁점, 답변요지, 쪽, 점수, 인용}], 안내?, 사례집에 없는 말?}. 검색어 낱말 절반 이상(드문 말일수록 무겁게)이 든 사례만 — 없으면 0건과 안내. 읽기 전용, 외부 호출 없음.

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": "casebook_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
kNo결과 수 1~10
areaNo분야 필터 (선택)
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
queryYes쟁점 문장이나 키워드

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.9.1
    • changedInput schema / properties / lang / description
      Previous value: -"Output language. 'en': English keys and labels, official English texts where available (tax treaties, statutes), titles/summaries machine-translated by Upstage Solar when UPSTAGE_API_KEY is set. 기본 'ko'"New value: +"Output 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'"
  2. Changed7 schema fields changedv0.4.0
    • changedInput schema / properties / area / anyOf
      Previous value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "enum": [
      +      "법인",
      +      "부가",
      +      "소득",
      +      "상증",
      +      "양도",
      +      "국기",
      +      "국조",
      +      "종부"
      +    ],
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • addedInput schema / properties / area / description
      Added value: +"분야 필터 (선택)"
    • addedInput schema / properties / k / description
      Added value: +"결과 수 1~10"
    • addedInput schema / properties / k / maximum
      Added value: +10
    • addedInput schema / properties / k / minimum
      Added value: +1
    • addedInput schema / properties / lang
      Added value: +{
      +  "default": "ko",
      +  "description": "Output language. 'en': English keys and labels, official English texts where available (tax treaties, statutes), titles/summaries machine-translated by Upstage Solar when UPSTAGE_API_KEY is set. 기본 'ko'",
      +  "enum": [
      +    "ko",
      +    "en"
      +  ],
      +  "title": "Lang",
      +  "type": "string"
      +}
    • addedInput schema / properties / query / description
      Added value: +"쟁점 문장이나 키워드"
  3. First observedv0.1.1

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already cover readOnly, idempotent, non-open-world, non-destructive, so the safety profile is a given; the description still adds real behavior: the match rule that more than half the query tokens (rarer tokens weighted heavier) must appear, and that an empty result returns 0 hits plus guidance rather than an error. It does not mention latency, rate limits, or ordering beyond the score field, so it is strong but not exhaustive.

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 purpose, then labeled blocks (언제 / 반환 / matching rule / read-only) that let an agent skim. Dense but every line carries information; the inline return-shape sketch is slightly heavy given there is no output schema to point to, but it earns its space.

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?

For a read-only, 4-parameter search tool with no output schema, the description covers the return fields (문서번호, 회신일, 분야, 쟁점, 답변요지, 쪽, 점수, 인용), the zero-hit case, and the retrieval threshold. Nothing an agent needs to call it or interpret an empty result is missing.

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 the schema already explains k (1-10), area enum, lang behavior, and query. The prose adds no parameter-level meaning beyond the schema — '검색어' is the only hint and it merely echoes the query description. Baseline 3 applies when the schema does the heavy lifting.

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 ('Search the NTS 2025 Tax Interpretation Casebook (96 curated cases)') with scope quantified as 96 curated cases, and explicitly differentiates from the sibling search_tax_rulings ('최신·전체 해석은 search_tax_rulings'). An agent can tell this is the fixed, curated subset rather than the live corpus.

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 an explicit when-to-use clause ('언제: 국세청이 대표 사례로 고른 해석을 빠르게 볼 때(오프라인, 즉시)') plus the alternative and the condition that selects it ('최신·전체 해석은 search_tax_rulings'). The read-only/no-external-call note removes ambiguity about side effects.

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