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

The annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the description's burden is lower. It adds contextual value by explaining classification severity (Class I=serious), status values, and the data source (FDA drug enforcement database, US public domain), which helps the agent interpret results. No contradiction with annotations.

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 sentences, each earning its place: action and scope, returned fields, filter syntax, and source/distinction declaration. The opening is specific and actionable, and there is no filler or redundant restatement.

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 read-only search tool, the definition covers what data is returned, how to filter, and how it differs from related recall domains. Pagination details are handled by the schema, and an output schema exists, so nothing needed for correct invocation is missing.

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%, with skip, limit, and search all documented in the schema. The description contributes Lucene syntax examples (e.g., recalling_firm:"Pfizer") that reinforce the search parameter, but this largely overlaps with the schema's own examples, so no significant new parameter-level meaning is added.

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 and resource ('Search FDA drug recall enforcement records'), quantifies the dataset (17,000+ actions), and enumerates the key return fields. It explicitly names sibling tools it is distinct from (device and food recalls), so an agent can differentiate this from adjacent tools without inspecting schemas.

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?

It provides explicit routing guidance: 'Distinct from device recalls (openfda_devices.recalls) and food recalls (health.food_enforcement) — this covers drug products only.' It also gives concrete Lucene query examples for the search parameter, showing how to formulate filters.

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