Skip to main content
Glama

내만집 (nmjib) — Korean semi-self interior renovation

접수 확인번호 대조(접수 2단계)

nmjib_verify_code
Idempotent

접수 1단계(nmjib_worker_apply·nmjib_consult_request·nmjib_partner_inquiry·nmjib_material_request) 뒤, 사용자가 문자로 받은 6자리 확인번호를 넣어 본인 확인을 마친다. 성공하면 접수가 확정되고 그때 담당자에게 전달된다. 틀리면 남은 시도 횟수를, 만료(10분)되면 resend=true 로 다시 보낼 수 있다(3회까지, 1분 간격). 문자가 안 왔다고 하면 resend=true 로 호출한다. 결과는 접수 상태와 다음 단계뿐이며 다른 데이터를 돌려주지 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": {
      "ticket": "<ticket>"
    },
    "name": "nmjib_verify_code"
  }
}

Input Schema

NameRequiredDescriptionDefault
codeNo문자로 받은 6자리 확인번호. resend=true 일 때는 생략
resendNo문자가 오지 않았을 때 true — 새 확인번호를 다시 보냄(3회까지, 1분 간격)
ticketYes접수 응답의 접수번호(예: AI-260910-K3P9Q)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.7/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, openWorldHint=false; the description adds what those hints cannot convey: success confirms the submission and forwards it to staff, failure returns remaining attempts, expiry is 10 minutes, and resend is capped at 3 times with a 1-minute interval. It also scopes the return value ('접수 상태와 다음 단계뿐'). The only residual gap is that resend=true triggers an outbound SMS on repeated calls, which sits slightly awkwardly with idempotentHint=true without being addressed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Roughly four sentences, front-loaded with the stage ordering, then the success/failure/expiry branches, then the return scope. No filler and no repetition of schema fields.

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 still tells the agent what comes back (intake status plus next step only), and it covers the retry and expiry branches an agent must handle. For a 3-parameter verification tool this is sufficient to invoke 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 baseline is 3, but the description goes further by explaining the operational meaning of resend (3 times, 1-minute interval, used when the SMS never arrived) and that the code is omitted in that mode. It does not restate the ticket pattern or code length, which the schema already covers.

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 states a specific verb and resource — verifying a 6-digit SMS code to complete identity confirmation — and explicitly positions it as '접수 2단계' following the four named stage-1 tools. An agent can distinguish this from nmjib_worker_apply and the other intake tools without opening any 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 explicit sequencing (only after stage 1), an explicit trigger for the alternative path ('문자가 안 왔다고 하면 resend=true 로 호출한다'), and the fallback when the code expires. When-to-use and when-to-use-the-other-mode are both stated, not implied.

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.