임신·출산·영유아 지원 서비스 찾기(보조금24 공공데이터)

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

Beyond the readOnly/idempotent/openWorld annotations, the description discloses operational traits the schema cannot: the list is cached for one day, region matching is an approximation derived from agency names, an external auth key (DATA_GO_KR_SERVICE_KEY) is required, and no application is performed. These are exactly the caveats an agent needs to avoid misreporting freshness or region precision.

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?

Four dense but purposeful sentences: purpose and output fields first, then caching/region caveats, then verification guidance, then the non-transactional disclaimer and auth requirement. Nothing is filler, though the parenthetical field enumerations make the opening sentence long.

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?

With no output schema, the description still enumerates the returned fields (서비스명·분야·대상·요약·신청처 with a detail link), and it covers caching, precision limits, auth prerequisites, and legal disclaimers. For a read-only four-parameter lookup tool, an agent has everything needed to call and interpret it correctly.

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 coverage is 100%, so the baseline is 3, but the description adds meaning not present in the schema: region filtering is approximate and based on agency name, and the tool's output is a summary rather than the full record. This contextualizes how much trust to place in the region parameter, though stage/limit/keyword semantics are largely restated from 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?

The description names a specific verb (select/summarize) and a specific resource (행정안전부 공공서비스 혜택 목록, 보조금24) scoped to 임신·출산·영유아. It goes further by listing the exact filter axes (생애 단계·키워드·지역) and the returned fields, so an agent can distinguish it from data-retrieval siblings at a glance.

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?

It clearly frames the tool as a reference lookup that does not process applications and tells the agent to confirm 자격·금액·신청 기간 via the detail link or the responsible agency. What is missing is an explicit comparison to overlapping siblings such as find_local_support, so the agent must infer that this tool covers pregnancy/childbirth/infant benefits rather than general local support.

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