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

Annotations already declare readOnly/openWorld/non-destructive, and the description goes well beyond them by enumerating the four possible decision values (recalled / possible_recall / no_recall_found / insufficient_evidence) and the per-notice payload (hazard, remedy, affected units, official link). It also flags the critical caveat that 'no_recall_found' is not a safety guarantee, which is exactly the behavioral context an agent needs before relaying a result to a user.

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 trigger condition is front-loaded and the important caveat closes the description, so the structure is sound. It loses some economy by restating the buying/selling/used-product condition twice and packing the product-category list into one long run-on clause.

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 seven optional parameters, no required fields, and no output schema, the description carries the full burden and does so: it explains accepted identifier shapes, what each data source covers, the shape of the result including the decision enum, and the interpretive limit on a negative result. An agent has enough to call it correctly and to report the result honestly.

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 71%, and the description adds routing meaning by mapping product categories to identifier types — UPC or brand/model for CPSC, year/make/model for NHTSA — and stresses that model numbers matter and should be sent when available. It complements rather than repeats the schema, though it doesn't clarify behavior when only partial identifiers are supplied.

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 names a specific action (search US government recall notices) and explicit data sources split by domain: CPSC for consumer products and NHTSA for vehicles. It states the input handles (brand/model, UPC, year/make/model), which lets an agent distinguish it from siblings like check_compatibility or identify_product without opening a schema.

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 trigger conditions are unusually explicit: before recommending, buying or selling anything used or secondhand, any kids' product, appliance, heater, battery device or vehicle, and when the user asks about safety or recalls. It does not name a when-not condition or point to a sibling alternative, so it falls just short of the top tier.

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