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

Beyond the read-only/idempotent annotations, the description reveals meaningful behavior: results are normalized and deduped within and across sources, severity-rolled with FDA Class I or death-related cases marked high, summarized by classification, and source failures are non-fatal. This gives an agent useful expectations about processing and error handling.

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 front-loaded with the main action, then covers input combinations, output processing, failure behavior, and verification caveat in a compact set of sentences. There is no wasted or misleading prose.

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 multi-source read-only tool with no output schema, the description covers what inputs are accepted and what the response will summarize, including deduplication, severity roll-up, classification breakdown, and partial source failure handling. An agent has enough context to invoke it 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?

Schema description coverage is 100%, so the schema already documents all six parameters. The description restates the query/vehicle combination at a higher level but does not materially add detail beyond the schema, which supports the baseline score.

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 a specific verb+resource combination: a one-call product-safety recall sweep across CPSC, openFDA, and NHTSA. It clearly distinguishes itself from sibling single-source recall tools such as cpsc_recall_search and fda_food_recalls by emphasizing the multi-source, normalized sweep.

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 usage context: use when a cross-source recall search is needed, supplying either a product/keyword/manufacturer query and/or a full vehicle identity. It stops short of explicitly naming alternatives or saying when to prefer a source-specific sibling, so it is clear but not fully explicit about exclusions.

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