Skip to main content
Glama

내만집 (nmjib) — Korean semi-self interior renovation

집주인 상담·작업자 매칭 문의(접수 1단계)

nmjib_consult_request
Idempotent

집주인이 내만집 담당자와 상담(반셀프 견적·공정별 작업자 매칭·공정 계획)을 원할 때 문의를 접수한다. 저장만 하고 되읽지 않는다. 호출하면 휴대폰으로 6자리 확인 문자가 가고 접수번호가 온다 → 문자의 번호를 받아 nmjib_verify_code 로 완료한다. 사용자가 명시적으로 "상담 받고 싶다/작업자 연결해 달라/연락 달라"고 할 때만 쓴다(이름·연락처·지역·평수·공사 범위를 물어보고 동의를 받은 뒤 consent=true). 작업자가 필요한 공정이 정해져 있으면 trades 에 넣는다(예: ["타일","도배"]). 금액 산출 도구가 아니다 — 비용 질문은 nmjib_cost_reference(후기 집계 범위)를 쓰고, 정확한 우리집 금액은 앱 견적을 안내한다. 작업자 명단·연락처를 돌려주는 기능은 없다.

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": {
      "name": "<name>",
      "phone": "<phone>",
      "consent": "<consent>",
      "region": "<region>",
      "scope": "<scope>"
    },
    "name": "nmjib_consult_request"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYes이름(또는 상호 담당자)
noteNo메모
phoneYes휴대폰 번호(010-1234-5678) — 이 번호로 6자리 확인 문자가 갑니다
scopeYes공사 범위. 예: "올수리", "욕실+주방", "도배·마루만"
pyeongNo평수
regionYes지역(시·구)
timingNo공사 희망 시기
tradesNo작업자가 필요한 공정(한글). 가능: 철거, 설비, 창호, 에어컨 청소, 에어컨 설치, 전기, 목공, 타일, 도장, 필름, 도배, 마루, 가구, 도기, 욕실, 마감. 예: ["타일","욕실"]
complexNo아파트·단지명
consentYes개인정보 수집·이용 동의. 사용자에게 수집 항목·목적·보유기간을 읽어 주고 명시적으로 동의를 받은 뒤에만 true. 수집 항목: 이름·휴대폰 번호와 신청 내용 · 목적: 담당자 연락과 접수 처리 · 보유: 180일 뒤 자동 삭제(요청 시 즉시) · 문의·철회: 1644-7233 · 정책: https://nmjib.com/privacy-policy

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / trades / description
      Previous value: -"작업자가 필요한 공정(한글). 가능: 철거, 설비, 창호, 에어컨, 전기, 목공, 타일, 도장, 필름, 도배, 마루, 가구, 도기, 욕실, 마감. 예: [\"타일\",\"욕실\"]"New value: +"작업자가 필요한 공정(한글). 가능: 철거, 설비, 창호, 에어컨 청소, 에어컨 설치, 전기, 목공, 타일, 도장, 필름, 도배, 마루, 가구, 도기, 욕실, 마감. 예: [\"타일\",\"욕실\"]"
  2. Changed1 schema field changed
    • addedInput schema / properties / trades
      Added value: +{
      +  "description": "작업자가 필요한 공정(한글). 가능: 철거, 설비, 창호, 에어컨, 전기, 목공, 타일, 도장, 필름, 도배, 마루, 가구, 도기, 욕실, 마감. 예: [\"타일\",\"욕실\"]",
      +  "items": {
      +    "type": "string"
      +  },
      +  "maxItems": 10,
      +  "type": "array"
      +}
  3. Added

TDQS

A4.4/5.0
Behavior3/5

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

Annotations already declare write semantics (readOnlyHint=false, destructiveHint=false, idempotentHint=true, openWorldHint=false), so the safety profile is partly covered. The description still adds real behavior beyond them: it stores without reading back, triggers a 6-digit SMS, returns a 접수번호, and requires a second step via nmjib_verify_code. It does not clarify what re-invocation does to the SMS/idempotency claim, which is the one gap.

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 the purpose, then the two-step flow, then the usage gate, then the exclusions — a sensible order with no filler sentences. It is dense and long-ish for one description, but each clause carries operative information.

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?

With 10 parameters, 5 required, no output schema, and a multi-step flow, the description covers what is needed: inputs to gather, consent handling, SMS/verification handoff, and the return of a 접수번호. An agent has everything required to call it correctly and to continue the flow.

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 meaning: trades should hold the specific 공정 the user needs (with a Korean example list), and consent must be true only after reading out the collection items and getting explicit agreement. The pyeong/region/timing fields are left to the schema.

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?

The description names a specific verb and resource (접수한다 / 상담·작업자 매칭 문의) and pins the actor (집주인). It also explicitly rules out what it is not — a cost-calculation tool — routing that case to nmjib_cost_reference, so an agent can distinguish it from siblings without opening the schema.

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?

It gives an explicit trigger (only when the user says "상담 받고 싶다/작업자 연결해 달라/연락 달라") plus the precondition sequence (ask name/phone/region/pyeong/scope, obtain consent, then consent=true). It names the follow-up tool nmjib_verify_code and the alternative for cost questions, leaving little to inference.

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.