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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), so the description's added value is the ordering guarantee, the weekly publication cadence with multi-day lag caveat, and the coverage boundary. That is meaningful context beyond structured fields, though return-shape detail is only partial.

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?

Front-loads the core action, then layers filtering, scope exclusions, and freshness in tight sentences. No filler and every sentence carries information an agent can act on.

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 no output schema, the description compensates by listing return fields (product, reason, lot codes, distribution regions, severity class) and adds the freshness caveat, so an agent knows what to expect without inspecting anything else.

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%, so the baseline is 3; the description earns a bump by clarifying query semantics ('Leave the query empty to list the latest recalls') and giving concrete example values (peanut butter, listeria, cucumbers) that map the free-text field beyond the schema's terse description.

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+resource ('Search US FDA food recall enforcement reports') and immediately scopes it with ordering ('newest first') and filter dimensions, which cleanly separates it from search_product_recalls and search_car_seat_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?

Explains the empty-query behavior ('list the latest food recalls') and draws an explicit boundary against USDA-covered meat/poultry/eggs. It gives clear when-to-use context, though it doesn't name a specific sibling to redirect to for those excluded products.

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