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

Annotations declare non-read-only, non-idempotent, open-world, non-destructive, but the description adds what the structured fields cannot: per-call cost (호출당 20포인트), a real side effect (휴대폰 알림 발송 및 접수 과금), and the explicit warning not to retry while pending — which is the practical consequence of idempotentHint=false. No contradiction.

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?

Five compact sentences ordered as purpose → cost warning → return/next-step → prohibition → price tag. No filler, and the cost caveat is placed early enough to gate the call.

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 5-param authentication-request tool with no output schema, the description supplies the return shape (transactionId, status), the follow-up tool, and the cost. There is no output schema to omit, and nothing an agent needs to invoke 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 100%, so name, birthDate, phone, authProvider, and incomeYears are already documented, including patterns and enum values. The description adds no field-level syntax or defaults beyond what the schema provides, so the baseline 3 applies.

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 and resource (본인 간편인증 요청) scoped to 금융소득(이자·배당) 조회, which cleanly separates it from the sibling get_personal_income that performs the actual retrieval. An agent can tell from the first sentence that this is the authentication handshake, not the data fetch.

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?

Explicit preconditions ('사용자 확인 후 호출하세요'), the downstream flow (return transactionId/status → phone approval → pass transactionId to get_personal_income), and a negative rule ('승인 대기 중 인증 요청을 반복하거나 자동 승인하지 마세요'). When-to-use, what-follows, and when-not-to are all covered.

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