APIbase

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

Annotations cover safety profile (readOnly, idempotent, non-destructive). Description adds value by identifying the external data source (OpenFDA) and domain scope, but omits rate limits, pagination behavior details, or return value structure.

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?

Single, efficiently structured sentence with main verb/resource front-loaded. Em-dash separates general function from specific examples; parenthetical identifies API source. Zero redundant words.

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?

Appropriately complete for a read-only search tool with simple parameters and good schema coverage. Identifies data domain and source. Lacks output schema description, but this is acceptable given no output schema exists to reference.

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%, establishing baseline 3. Description implicitly supports the 'search' parameter by listing example query contexts (contamination, mislabeling) but does not explicitly document parameter syntax or constraints beyond schema.

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?

Description uses specific verb 'Search' with clear resource 'FDA food enforcement and recall reports'. The parenthetical examples (contamination, mislabeling, safety alerts) and 'OpenFDA' source clearly distinguish this from siblings like vehicle.safety.recalls and health.safety.drug_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?

Provides clear context through specific examples of recall types (contamination, mislabeling, safety alerts) that guide when to use the tool. However, lacks explicit 'when-not-to-use' guidance or named alternatives for drug/vehicle recalls.

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