Skip to main content
Glama

Define Term (용어 정의)

define
Read-onlyIdempotent

Retrieves the definition of a single Korean AEC term for "what is X" questions, returning the term's meaning without numeric standards or code clauses.

Instructions

건축·건설 용어 하나의 뜻을 돌려줍니다. '이형철근이 뭔가', '방화구획이란', '옹벽과 흙막이의 정의' 같은 'X가 무엇인가' 질문에 호출합니다. → 대체 도구: 수치·조문이 필요하면 k_snippets · 종류/체계 열거는 enumerate · 왜 그런지는 answer_why · 두 개념 차이는 compare · 두 개념이 어떻게 이어지는지는 path_between. 이 도구는 정의 한 덩어리만 주고 기준 수치는 주지 않습니다. ★파라미터: term에는 용어 하나를 입력합니다(질문 문장이나 여러 용어의 나열은 입력하지 않습니다). limit는 동음이의로 후보가 나뉠 때 몇 개까지 볼지를 정하며 1~5로 잘립니다(기본 3). as_of는 YYYY-MM-DD입니다. ★abstained=true이면 Den이 그 용어의 정의를 갖고 있지 않다는 뜻입니다. 비슷한 말을 지어내지 않고 그대로 전한 뒤 다른 출처로 답합니다. exact=false는 이름이 정확히 일치하지 않는다는 표시이므로 이름이 맞는지 확인하고 씁니다. 읽기 전용이며 외부 호출이 없습니다.

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": {
      "term": "<term>"
    },
    "name": "define"
  }
}

Input Schema

NameRequiredDescriptionDefault
termYes정의를 물을 용어 하나(예: 이형철근).
as_ofNo과거 발주도서나 분쟁에서 '당시 기준'을 물을 때 씁니다. 예: as_of=2020-06-01
limitNo동음이의로 후보가 나뉠 때 볼 후보 수(1~5).

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.2.5

TDQS

A4.6/5.0
Behavior4/5

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

Goes well past the annotations by disclosing two result-state semantics: abstained=true means Den holds no definition and will not invent a plausible-sounding substitute, and exact=false flags an inexact name match that must be verified. It also notes limit clamps to 1–5. It loses a point only for restating '읽기 전용이며 외부 호출이 없습니다', which merely repeats readOnlyHint/openWorldHint.

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 alternatives, then parameters, then result-flag semantics — a clean and scannable ordering that fits a dense Korean-style spec. Minor waste in the closing sentence that repeats what the annotations already declare.

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?

Output schema exists, so return values need no prose, yet the description still explains the two output flags an agent must act on (abstained, exact). For a single-term lookup with 3 params this covers everything needed to call it and interpret the response correctly.

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 3 is the baseline, but the description adds genuine constraint: term takes exactly one term and must not receive a question sentence or a list of terms — a failure mode the schema's '용어 하나' does not spell out. It also gives as_of's YYYY-MM-DD form and confirms the 1–5 clamp on limit with default 3.

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: '건축·건설 용어 하나의 뜻을 돌려줍니다' with concrete example phrasings ('이형철근이 뭔가', '방화구획이란'). It also explicitly draws the boundary against five named siblings, so an agent can select it without opening other schemas.

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?

Names the triggering question shape ('X가 무엇인가') and then routes each adjacent need to a specific alternative: k_snippets for numbers/clauses, enumerate for taxonomies, answer_why for causation, compare for differences, path_between for relations. It also states an explicit exclusion — '이 도구는 정의 한 덩어리만 주고 기준 수치는 주지 않습니다' — so over-reach into numeric questions is prevented.

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