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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered. The description adds useful operational context (max 100 results, headline-only fields) but is silent on pagination via cursor and on how results are ordered, which matters for a capped search.

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?

Two dense sentences, front-loaded with purpose and sources, then filters, then return shape and exclusions. Nearly every clause carries information; only the exhaustive authority name list is mildly over-specified.

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 12 parameters, no output schema, and thin schema descriptions, the definition should say more about the return shape and the cursor-based pagination. It does supply a result cap and 'headline fields', which is the minimum an agent needs to call it without surprises.

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 only 25% across 12 parameters, so the description carries real weight: it explains that q is free text, that authority/jurisdiction/category/hazard/manufacturer are filters, and that is_recall separates strict recalls from other classified actions. It omits limit, cursor and risk_level, and doesn't clarify how free text interacts with the structured filters.

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 (search) and resource (consumer-product safety notices), names the six source authorities, and carves out what is not covered (FDA food/drug/device and vehicle recalls). That gives an agent a clear picture of content, though it does not contrast the tool with its siblings recalls_get and recalls_sources.

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?

There is real when-not guidance: the FDA and vehicle exclusions tell an agent when this tool will return nothing. However, nothing says when to use this versus recalls_get for full notice detail or recalls_sources for coverage, so the choice between siblings is left implicit.

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