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

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, covering safety and idempotency. The description adds valuable behavioral context: 'No auth — US Consumer Product Safety Act public domain data, unlimited free' and 'Database contains all recalls since 1974 — over 6 000 active recall records,' which informs expectations about scope and access without contradicting annotations.

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 six sentences, each with a distinct purpose: what it does, return fields, data scope, typical use case, and authentication status. It is front-loaded with the action and resource, and while slightly more verbose than strictly necessary, no sentence is redundant.

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 read-only search tool with 8 optional parameters, an output schema, and full annotations, the description is largely complete: it covers purpose, returns, data depth, authorization, and a representative use case. The only minor gap is that it doesn't mention how to narrow results if too many match — but the schema's limit parameter description already covers that, so the description is sufficient.

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 description coverage is 100%, so the baseline is 3. The description lists the search dimensions (product name, category, manufacturer, date range, hazard, country) but adds no new semantics beyond what each parameter's description already provides. It does not explain interactions or precedence between parameters, so it stays at the baseline.

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 opens with 'Search US Consumer Product Safety Commission (CPSC) recall notices by product name, product category, manufacturer, date range, hazard type, and country of origin' — a specific verb, resource, and multi-criteria scope. It also states what is returned (title, description, hazards, remedy options, manufacturer details, URL) and distinguishes itself from sibling tools like cpsc.safety.recent and cpsc.safety.by_manufacturer by being the general search across all criteria.

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 a clear use case: 'Use to check whether a specific product or brand has been recalled for safety defects, fire hazards, choking risks, or other consumer safety issues.' It does not explicitly exclude or direct to sibling tools like cpsc.safety.recent or cpsc.safety.detail, but the context of a broad recall search is clear, satisfying 'clear context, no exclusions'.

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