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

Goes well beyond the readOnly/idempotent annotations by disclosing the actual return shape (petal_id, accepting_requests, prefilled_fields, missing_required), the low-confidence fallback that returns a category list instead of a match, and the special-case behavior that 'Health is web-only' returns a message rather than a form. That is exactly the runtime behavior an agent needs before calling.

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 tight sentences, front-loaded with the core mapping action and followed by return values and the two edge cases. No filler and nothing repeated from the schema.

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 carries the burden of explaining returns and does so thoroughly, including the unmatched fallback and the web-only Health exception. An agent has everything it needs to call this and interpret the result.

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 schema already documents 'text' (the customer's own words) and 'region'. The description adds no format, constraint, or interpretation detail beyond that, so the baseline 3 applies.

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?

States a specific verb+resource: mapping the customer's free text to a Bidit category. Combined with the returned field names (petal_id, prefilled_fields), an agent can tell this router/classifier apart from the create_request/submit_request siblings without opening their schemas.

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?

Usage is implied by outputs like missing_required and prefilled_fields, which signal this is the discovery step before get_request_form or create_request, but the description never explicitly says when to call it or what to call next. No exclusions or alternatives are named.

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