Skip to main content
Glama

내만집 (nmjib) — Korean semi-self interior renovation

공사 안내문 만들기

nmjib_construction_notice
Read-onlyIdempotent

아파트 인테리어 공사 안내문(엘리베이터 · 게시판에 붙이는 이웃 안내문)을 만든다. 단지명 · 동호 · 공사 시작일 · 평형을 주면 내만집 공개 공정표 양식(24 · 30 · 40평 영업일)으로 공정별 날짜를 채우고 요일 · 쉬는 날(일요일 · 토요일 · 공휴일) · 소음 큰 날 · 관리사무소 확인 칸까지 넣은 안내문 본문(마크다운 표)과, 같은 내용이 채워진 내만집 만들기 화면 링크(A4 인쇄 · 워드 파일 받기)를 돌려준다. 양식 5종: full=전체 공사(올수리) · demolition=철거·샷시(창호) 교체 · bath=욕실·주방 부분 공사 · finish=도배·마루·도장 · change=일정 변경·연장. "공사 안내문 써줘", "엘리베이터에 붙일 인테리어 공사 공지", "공사 안내문 양식" 요청에 쓴다. 응답의 안내문 표와 링크를 그대로 보여 준다. 전화번호는 묻지도 넣지도 않는다 — 연락처 칸은 사용자가 링크 화면에서 채운다. 저장 · 전송 없음.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "nmjib_construction_notice"
  }
}

Input Schema

NameRequiredDescriptionDefault
pyNo평수. 24 · 30 · 40평 공정표 양식 중 가장 가까운 것으로 날짜를 센다(기본 30).
aptNo단지명(예: 래미안대치팰리스). 안내문 제목과 공사 세대 줄에 들어간다. 모르면 비운다.
tplNo양식. full=전체 공사(올수리) · demolition=철거·샷시(창호) 교체 · bath=욕실·주방 부분 공사 · finish=도배·마루·도장 · change=일정 변경·연장full
unitNo동 · 호수(예: 101동 1203호). 모르면 비운다(○ 칸으로 남음).
startNo공사 시작일 YYYY-MM-DD. 양식 full 이면 이 날부터 공정표 양식으로 공정별 날짜를 채운다.
processesNo공정 목록(선택). name 만 주면 공정표 양식에서 그 공정만 남기고, start · end(YYYY-MM-DD)를 주면 그 날짜를 쓴다. 비우면 양식 기본 공정.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real behavioral context beyond them: exactly what is filled in (dates per process, weekday, Sunday/Saturday/holiday rest days, noisy days, management-office confirmation column), that the output is a markdown table plus a link to the print/Word screen, and that nothing is saved or transmitted. It also discloses a non-obvious constraint — it will not ask for or include phone numbers, leaving the contact field to the user on the linked screen — which the agent could not infer from any structured field.

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 and output, then usage triggers, then the contact-number constraint and no-storage note, so the important parts come first. It loses a point for duplicating the five-template enumeration that already appears in the tpl enum description, a sentence that does not earn its place twice.

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 no output schema, the description carries the return-value burden itself and does so fully: table contents, the accompanying link, and the print/Word affordances. Annotations cover the safety profile and the description covers the empty-unit '○' fallback and the no-phone-number rule, so an agent has everything needed to call this with zero required parameters and present the result correctly.

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 are already documented, and the description largely restates them: the five template codes, the nearest-of-24/30/40 sizing, and the processes list behavior all appear verbatim or near-verbatim in the schema. Baseline 3 applies; the description adds little semantic meaning the schema does not already carry.

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 ('아파트 인테리어 공사 안내문...을 만든다') and pins down the scope: an elevator/board notice for neighbors, not a general document tool. It also names the exact artifacts produced (markdown process table plus a pre-filled nmjib screen link), which separates it from siblings like nmjib_process_guide or nmjib_checklist without the agent needing to open another schema.

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?

Gives concrete trigger utterances ('공사 안내문 써줘', '엘리베이터에 붙일 인테리어 공사 공지', '공사 안내문 양식'), which is strong when-to-use guidance. It also instructs the agent to render the returned table and link verbatim. It stops short of naming a sibling to use instead for adjacent needs (e.g., cost estimates or process explanations), so no explicit exclusions.

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.