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

Annotations provide openWorldHint=true and readOnlyHint=false, but the description goes far beyond by specifying how to interpret results ('0件を制度不存在とせず'), how to handle specific use cases (employment/training), and that the response contains guidance to follow. It also warns against concluding eligibility solely from search results. These are critical behavioral details that are not in the annotations, adding substantial value.

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 a single, dense paragraph that leads with the core purpose and scope, then layers operational instructions. Every sentence carries essential information – there is no fluff or repetition. The structure flows logically from what the tool does to how to use it correctly, making it easy for an agent to parse.

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?

Given the tool has 9 parameters, no output schema, and a complex operational context, the description covers all critical aspects: scope, handling of zero results, follow-up actions (get_subsidy_detail), and external supplementation. It even references response guidance, acknowledging that the output will contain instructions. An agent has enough to invoke and interpret results 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?

The schema covers 67% of parameters with descriptions, and the description adds semantic context for at least one parameter: '所在地が指定された場合は全国対象制度も含めます' clarifies the behavior of the target_area parameter. It also implies that employee_count is used for post-API filtering, though that is already in the schema. The description does not explicitly describe sort, limit, or order, but those are straightforward. Overall, it enhances parameter understanding beyond 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 states the specific verb ('検索' – search), the resource ('Jグランツの公開API' – J-Grants public API), and the subject ('補助金候補' – subsidy candidates). It explicitly scopes the search to J-Grants, which distinguishes it from sibling tools like get_subsidy_detail (which fetches details) and search_companies (which searches companies). The purpose is unambiguous and well-differentiated.

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 operational guidance: follow the returned searchGuidance and responseGuidance, do not treat zero results as non-existence, supplement with standard web search for employment/training using MHLW official information, include nationwide programs when a location is specified, and use get_subsidy_detail after candidate selection. It also implicitly tells when not to use this tool (not for final eligibility determination). This is exemplary guidance for an agent.

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