req_nps_join_history국민연금 가입내역 조회를 위한 본인 간편인증을 요청합니다. 휴대폰 알림 발송과 접수 과금이 발생하므로 사용자 확인 후 호출하세요. transactionId와 status를 반환하면 휴대폰 승인을 안내하고, 승인 후 get_nps_join_history에 transactionId를 전달하세요. 승인 대기 중 인증 요청을 반복하거나 자동 승인하지 마세요. [호출당 20포인트]
| Name | Required | Description | Default |
|---|---|---|---|
| to | No | 조회 종료 월 (YYYY-MM, 선택) | |
| from | No | 조회 시작 월 (YYYY-MM, 선택) | |
| name | Yes | 본인 이름 | |
| phone | Yes | 본인 명의 휴대전화 번호 (숫자만) | |
| birthDate | Yes | 생년월일 8자리 (YYYYMMDD) | |
| authProvider | Yes | 휴대폰에서 승인할 간편인증 방식 |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only tell it is not read-only and not idempotent. The description adds crucial beyond-schema behavior: SMS push notification is sent, billing is incurred (접수 과금, 호출당 20포인트), returns transactionId+status, and warns against duplicate auto-approval requests. This is exactly the extra context annotations cannot express.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tight, front-loaded sequence: purpose → caution → return value/next step → prohibition → cost. Every sentence earns its place with zero filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a cost-incurring, async, user-confirmation-gated auth-initiation tool with no output schema, the description covers purpose, prerequisite (user confirmation), return values (transactionId, status), handoff to get_nps_join_history, anti-patterns, and cost. Nothing an agent needs to call it correctly is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is already 100% with all six params documented, so description adds no param-level detail. It does mention transactionId/status as outputs, which is helpful since no output schema exists, but does not explain the from/to query range parameters beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (요청/인증 요청) and resource (국민연금 가입내역 조회). Clearly distinguishes itself from the sibling get_nps_join_history by naming it as the follow-up step, and from other req_* sibling tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly tells when to call (사용자 확인 후), how to proceed after (휴대폰 승인 안내 후 get_nps_join_history에 transactionId 전달), and what not to do (승인 대기 중 반복 요청, 자동 승인 금지). Alternative/sibling routing is named directly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.