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

Annotations already declare readOnlyHint=true, so the safety profile is covered externally. The description adds useful context by naming the backing endpoint (openFDA drug/enforcement) and the fields returned, but says nothing about result caps, pagination limits, or rate limiting beyond what the schema states.

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 sentences: the first front-loads purpose and the returned content, the second pins the data source. No filler or restated title padding.

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 usefully enumerates the fields each recall record carries, so an agent knows what comes back. Only minor gaps remain, such as default result behavior and pagination limits, which the schema's parameter text already handles.

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 skip, sort, limit, and search are fully documented in the schema itself, including Lucene syntax and range examples. The description adds no parameter-level meaning beyond that, so the baseline 3 is appropriate.

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?

Specific verb (Search) plus a precisely scoped resource (drug recall enforcement reports), and it enumerates what each report contains (reason, classification Class I/II/III, recalling firm, distribution, status). The 'drug' qualifier and the 'drug/enforcement endpoint' note clearly separate it from sibling recall tools like search_device_recalls and search_food_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 drug-specific framing implies when this tool applies versus the device/food recall siblings, but there is no explicit when-to-use, when-not, or reference to alternatives such as openfda_query or count for aggregate questions. Usage is inferable but never stated.

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