japan_company_search

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

With no annotations, the description carries the full disclosure burden and does so well: it states that retrieval runs fully offline, that 'vector' and 'hybrid' require a ~220MB one-time model download, that the Free edition is limited to 192 blue-chip companies, and that results are ranked by relevance. This gives the agent accurate expectations about limitations, side effects, and output shape.

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 dense but every sentence earns its place: purpose, scope, return values, limitations, download caveat, and routing to sibling tools are all present without fluff. It is front-loaded with the core purpose and then layers behavioral and usage details logically.

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 3-parameter search tool with no output schema and no annotations, the description is complete. It explains what the tool returns, when to use it, how to choose methods, what limits apply, what network/download behavior to expect, and which sibling tools to call next. No critical context for invoking the tool 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 coverage is 100% for all three parameters, so the baseline is 3 (schema carries the load). The description adds meaningful method guidance beyond the schema by explaining offline behavior, the download triggered by certain methods, and suitability of 'trigram' vs 'hybrid' for different query types. It doesn't add much for top_k, but the schema already documents it.

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 uses specific verbs and a resource ('Search across Japanese corporate registries and listed-company filings') and explicitly frames the tool as 'the entry point when the target company is unknown or ambiguous.' It names the return payload (ranked companies with name, corporate number, securities code, snippet), clearly distinguishing it from the detail-oriented 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?

The description gives explicit when-to-use guidance ('Use this to resolve an entity first') and names the follow-up alternatives exactly: edinet_financials_usgaap, japan_shareholders, and japan_corporate_registry. It also provides method-level selection advice: 'trigram' suits codes and identifiers, while 'hybrid' suits natural-language queries.

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