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

Annotations already declare read-only, idempotent, open-world, non-destructive, so safety needs no restating. The description instead adds behavior the annotations cannot: results are sorted newest first, records contain the product/reason/firm/FDA class/sales area in the agency's own words, and free-tier data is capped at 14 days. Pagination or truncation behavior is left unstated.

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?

Four short sentences, each earning its place: what data, what each record holds, the url-attribution instruction, and the free-tier limit. The core identification is front-loaded and there is no filler.

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 an output schema present, the description need not enumerate return fields, yet it still summarizes them and pins down the source split and freshness cap — enough for correct invocation. It stops short of explaining matching behavior (e.g., whether 'query' is substring or full-text) beyond what the schema says.

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 100% with enums and defaults documented, so the schema carries the parameter burden. The description adds only indirect context — that 'category' maps to CPSC vs FDA sources and that FDA classification grades exist — which the schema already states. Baseline 3 applies.

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?

Names a concrete resource (US product recalls) plus the two authoritative sources (CPSC consumer products; FDA food/drug/device enforcement reports) and the sort order (newest first). This immediately separates it from all siblings, which cover awards, contracts, jobs, permits, regulations and news rather than recalls.

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 data coverage stated ('consumer products from CPSC' vs 'food, drugs and medical devices from FDA') tells an agent which questions this tool answers, and 'A free key reaches the last 14 days' sets an explicit freshness boundary the agent must respect. No explicit when-not or named alternative is given, though no sibling overlaps enough to need one.

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