search_knowledge

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

No annotations are provided, so the description must carry the full burden. It discloses that 'vector' and 'hybrid' trigger a one-time ~220MB embedding model on first use while 'bm25' and 'trigram' always work offline, and that this Free edition indexes only 192 blue-chip companies. It does not mention caps on top_k or pagination behavior, which amounts to an otherwise minor omission.

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 about 60 words in a single paragraph with a clear topic, method details, domain-alternative guidance, and edge cases. A significant quote here, 'bm25' for exact keywords, is scoped correctly. It is a bit dense and could be split with a sentence dedicated to method guidance, but every sentence contributes valuable information.

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 tool with no output schema and no annotations, the description covers many things: the result type ('ranked text records'), the content fields (registry, EDINET, major shareholders, gBiz pays, benchmarks), the index limit of 192 companies, and download-required methods. The only gap is an explicit result size/pagination limit, but this is not essential for invoking the tool 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?

All three parameters have descriptions in the input schema, so the baseline is 3. The description adds guidance on method selection – 'bm25' for exact keywords, 'trigram' for codes/identifies, 'vector' for semantic, 'hybrid' for mixed – which gives an agent further reason for choosing a method.

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?

Specific verb and resource: 'Search the Japanese corporate knowledge base' with explicit method mention ('raw keyword, fuzzy, semantic, or hybrid retrieval'). It also frames itself as the 'flexible fallback for open-ended questions the domain tools do not cover' and names the sibling tools as alternatives, making its distinct place in the family clear without opening a schema.

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?

Provides explicit when-to-use for the domains: 'Prefer the domain tools (edinet_financials_usgaap, japan_corporate_registry, japan_shareholders, japan_industry_benchmarks, japan_company_search) for structured questions; use this for cross-cutting or exploratory queries.'

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