FDA Approvals

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

No annotations are provided, so the description carries the full burden. It discloses the deduplication behavior and a bug fix (v0.2.1), which adds transparency. However, it does not mention whether the tool is read-only, rate limits, data freshness, or any side effects. Given the lack of annotations, a 4 is appropriate as it provides notable behavioral context beyond a minimal description.

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 two sentences, extremely concise, and front-loaded with the key verb 'aggregate' and the resource. Every word adds value, with no redundancy.

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?

No output schema is provided, but the description explains the return values (total reports, unique reaction count, top 20). The parameters are partially explained, and the tool's functionality is clear. For a 4-parameter tool with no output schema, the description is reasonably complete, though date formats and limit semantics could be clearer.

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 25% (only the 'drug' parameter has a description). The description adds meaning by stating 'drug' is a generic name and implies that 'date_from' and 'date_to' define the window, but does not specify date format or explain 'limit'. The description compensates partially but not fully for the low schema coverage.

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 FDA adverse event reports for a drug, specifies deduplication, and lists the output (total reports, unique reaction count, top 20). It distinguishes itself from sibling tools (fda_drug_approval_search, fda_drug_label, fda_recall_search) by focusing on 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 does not explicitly specify when to use this tool versus alternatives. It mentions a bug fix but lacks guidance on appropriate contexts, prerequisites, or when not to use it. The sibling tools are clearly different but no direct comparison or exclusion criteria are provided.

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

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

No annotations are provided, so the description carries full burden. It indicates a read-only search operation and lists return fields, but does not disclose pagination behavior (skip/limit), rate limits, data freshness, or safety implications. While it implies non-destructive use, explicit behavioral traits are missing.

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?

Two efficient sentences: the first states the action and source, the second summarizes filters and return fields. No fluff; every part adds value.

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 7-param tool with no output schema or annotations, the description covers the core functionality and return values but lacks details on pagination, error handling, and data scope. It provides a good overview but not full completeness for an AI agent to handle all usage scenarios.

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?

The description adds meaning by grouping filter parameters (sponsor, brand, generic, date range) and explaining their purpose. Schema description coverage is 57%, and the description compensates for the undocumented params like skip and limit by implying their role in pagination, though not explicitly.

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 searches FDA drug approvals from Drugs@FDA, listing specific filters and return fields (application number, sponsor, brand/generic name, approval date). This distinguishes it from sibling tools that cover adverse events, labels, and recalls.

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 explains what filters can be used but does not provide guidance on when to use this tool versus alternatives like fda_adverse_events or fda_recall_search. No explicit when-not or alternative recommendations are given.

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

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

No annotations are provided, so the description carries full burden. It lists contents but does not disclose rate limits, data freshness, whether the response is a full label or summary, or any potential side effects like missing data for certain drugs.

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?

Two sentences: first sentence states the core action and resource, second lists key content areas. No redundant information, highly efficient.

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?

No output schema exists, so description should explain return structure. It mentions included sections but does not specify format (JSON, text), hierarchy, or error handling. Adequate for a simple single-parameter tool but incomplete for agents needing precise return expectations.

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% (only one parameter with description). The description adds example values ('Ozempic' or 'semaglutide') and clarifies brand/generic, providing marginal additional guidance beyond the 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?

The description clearly states the action ('Fetch'), the resource ('FDA-approved drug label'), and lists key contents (indications, dosage, etc.), distinguishing it from sibling tools like fda_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 implies use for label information, but does not explicitly state when to use this tool versus alternatives (e.g., sibling tools) or provide any exclusions or prerequisites.

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

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

No annotations are provided, so the description carries full burden for behavioral disclosure. It mentions that the tool returns specific fields, but fails to disclose important behaviors such as pagination, rate limits, data freshness, or whether the operation is read-only. The description is insufficient for a tool with no annotation support.

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 a single sentence that effectively front-loads the core purpose and key details. Every word carries value, with no redundancy or wasted space.

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?

Given the tool has 5 parameters, no output schema, and no annotations, the description provides adequate but incomplete information. It lists returned fields and filter types, but lacks details on pagination—given the 'limit' parameter—date formatting, error handling, or result size expectations. Some gaps remain.

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. It explains the 'product_class' enum and the concept of date range, adding meaning beyond the schema. However, it does not explain the 'limit' parameter, the 'domain' enum values (though domain is hinted at in the purpose), or the format of date parameters. Coverage is partial.

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 searches for recall events in drug, device, or food domains, and lists key filters (classification, date range) and returned fields (recall number, classification, reason, firm, status). This distinguishes it from siblings like 'fda_adverse_events' which focus on 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 explains what the tool does and its filters, but does not explicitly state when to use it versus alternatives or when not to use it. The usage context is implied by naming and description, but no explicit guidance is provided.

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