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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, openWorldHint=false), so the bar is lower. The description adds useful context on source coverage and result ranking ('newest and most relevant first'), but says nothing about pagination, result volume caps, or cost/latency behavior.

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 tight sentences: the core operation and sources come first, ordering and filtering follow. No filler, nothing redundant with structured fields.

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?

No output schema exists, so the description could usefully say what a result looks like (recall fields, links) and how deep result sets go, but it does not. For a 4-parameter search over 19 categories it is adequate but leaves the agent guessing on result shape and the limit parameter.

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 50%: query and since have descriptions, while limit and category do not. The description hints at category and date filtering, which partially compensates, but the 'limit' parameter and the semantics of the 19-value category enum receive no explanation. Baseline 3 fits.

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 and resource: full-text search across US recalls, with the three source agencies named (CPSC, FDA, NHTSA) and the result ordering disclosed. It does not explicitly differentiate itself from siblings like get_recall or check_product, which prevents a 5.

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 'filter by category and date' and the word 'search', but there is no explicit statement of when to use this versus get_recall (lookup a known recall) or check_product/check_vehicle (entity-specific checks). The agent must infer the routing itself.

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