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

Annotations already mark this as read-only and non-destructive, and the description adds useful behavioral context: it returns recall classifications, describes what Class I/II/III mean, notes that Class I recalls trigger press releases and procurement review obligations, and cites OpenFDA Enforcement Reports as the source. This goes beyond the annotations without contradicting them.

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 description is longer than average but front-loaded with the use case and return value, then supported by a concrete example, source citation, and pricing. Most sentences earn their place, though the example is somewhat elaborate.

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 two-parameter read-only tool with no output schema, the description covers the main needs: when to use it, what it returns, an illustrative example, the data source, and cost. The main gap is the lack of explicit parameter-level instructions, especially for product_type.

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 0%, so the description must compensate for the undocumented company_name and product_type parameters. It implies product type via 'pharmaceutical company' and 'medical device manufacturer', but never explicitly explains the product_type enum values, the default of 'both', or how company_name should be formatted.

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 clearly states the tool 'Returns FDA recall classifications' with product descriptions and recall reasons, anchored to a specific evaluation use case. It is distinct in subject matter from most siblings, but it does not explicitly differentiate itself from closely related tools like get_drug_recall_status or get_openfda_adverse_events.

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 description opens with 'Use when evaluating a pharmaceutical company, medical device manufacturer, or healthcare vendor' and names the relevant risk areas, giving clear context for when to invoke it. It does not, however, state when to prefer an alternative tool or when not to use this one.

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