fda_drug_counts

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety profile is clear. The description adds that it aggregates/counts data, but doesn't disclose behavioral nuances like pagination, rate limits, or what happens when no results are found. It also doesn't mention potential large result sizes or performance implications, but the default limit and max are in the schema.

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 concise and well-structured. It front-loads the core purpose, then provides usage guidance with a list of common fields. Each line provides distinct value without redundancy. It doesn't waste words on restating schema details.

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 fairly simple parameter structure (3 params, 1 required) with complete schema coverage, the description is adequate. It provides key usage guidance and examples. However, it lacks details on the output format (though no output schema exists, the agent might benefit from knowing what the count response looks like) and doesn't explain the relationship between search and count_field (e.g., whether search can filter before counting).

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 parameters are documented. The description adds value by explaining the '.exact' suffix usage and providing concrete examples of count_field values. It also explains the search parameter with an example ('patient.drug.openfda.brand_name:aspirin'), which helps the agent construct valid queries beyond the schema's basic description.

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 aggregates/counts FDA drug adverse event data by any field, with a specific verb ('Aggregate/count') and resource ('FDA drug adverse event data'). It also names a sibling tool (fda_count) for other endpoints, distinguishing it from alternatives. The list of common count fields adds concrete use cases.

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 explicitly says to use fda_count for other endpoints, providing a clear alternative. It also gives common count fields with examples, implying when each is useful. However, it does not explicitly state when NOT to use this tool beyond the fda_count mention, or describe edge cases like when the search parameter is needed.

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