search_audit_case

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

With no annotations, the description carries the full burden of behavioral disclosure. It reveals that search results contain nttId and that get_audit_case is needed for actual reasons and judgment bases, implying results are summaries. It also explains that keyword_variants increases recall, adding beyond the schema. The page-ignoring behavior for keyword_variants is not mentioned here but is in the input schema, so the description does not contradict nor fail to disclose any critical behavior.

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?

The description is two sentences, both purposeful. The first sentence front-loads the main purpose, and the second sentence efficiently covers the follow-up call and keyword_variants guidance. There is no fluff or repetition of schema details.

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 search tool with no output schema and 5 parameters, the description covers the essential flow: search, then use the returned nttId with get_audit_case for full details. It also addresses a specific edge case (approximate knowledge) and how to handle it. It does not describe the result list structure or pagination, but the schema provides parameter details, so the description is sufficiently complete for a non-destructive search operation.

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 80%, so the baseline is 3. The description adds genuine meaning to keyword_variants: when to use it, why (recall), and provides a concrete example with multiple search terms. This elaborates on the schema's description, which already detailed the parameter, but the main description makes the use case clearer, elevating it to a 4.

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 clearly states the tool's function with a specific verb and resource: '금융감독원 심사·감리지적사례(회계처리 위반 지적 사례집)를 검색합니다' (searches FSS review/supervision noted cases). It also differentiates from siblings by immediately linking to get_audit_case, showing the follow-up workflow and peculiar use.

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?

The description provides explicit context for when to use keyword_variants: '회사명·정확한 쟁점을 모르고 사건 내용만 대략 아는 경우' (when you don't know the company name or exact issue and only roughly know the case). It also advises to call get_audit_case with the nttId for full PDF details, giving a clear next step. However, it does not explicitly mention when not to use this tool or contrast it with alternative search tools like search_sanction.

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