openfda_enforcement

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

The description goes far beyond the readOnlyHint and openWorldHint annotations. It discloses keyless operation with a specific rate limit (~1000 requests/day), explains that the key never causes errors, and details exact error semantics (404→honest empty, 400→invalid_input with message, 5xx→throw, 200 non-JSON→schema_drift). It also reveals return format, pagination honesty (using totalAvailable and hasMore/nextOffset), and null-handling policy (null-never-empty-string). This is exemplary transparency.

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 long but well-structured, with clear sections for purpose, keyless behavior, inputs, return format, and error handling. It front-loads the core purpose and then layers details logically. While verbose, every sentence provides actionable information; no filler. The use of bullet points and symbols (★) aids scanning. It earns a 4, slightly penalized for length that could be trimmed without losing meaning.

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 9-parameter tool with no output schema, the description is remarkably complete. It specifies the exact return object structure with field names, explains pagination via _meta.pagination.nextOffset, documents error mapping for every plausible HTTP status, and even notes that recall_initiation_date is a YYYYMMDD string. Nothing an agent needs to call this tool correctly 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 coverage is 100% with descriptions for all 9 parameters. The description adds value beyond the schema by mapping each filter to the openFDA field name (→ recalling_firm, etc.), noting that values are escaped into a Lucene string, and clarifying the default for category and the range for limit. This goes beyond a baseline 3, though it doesn't dive into syntax details for every parameter; the schema already covers validation (e.g., state regex).

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 openFDA recall/enforcement records — drug/device/food product recalls'. It lists the exact data elements returned (recalling firm, product, reason, classification, status, geography) and explicitly names the endpoint (api.fda.gov/{category}/enforcement.json). This is unambiguous and distinguishes it from sibling tools like openfda_device_clearances or nhtsa_recalls, which focus on different datasets.

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 provides extensive usage guidance: explains the optional API key behavior and rate limits, details how each filter maps to an openFDA field (e.g., firm→recalling_firm, product→product_description), explains the default category, and lays out pagination via skip/limit. It also covers error handling for common cases (404→empty, 400→invalid_input, 5xx→throws). It does not explicitly name alternative tools for different data needs, but the scope is so clearly defined that an agent can route appropriately.

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