Aggregate FDA adverse-event reports (FAERS) for a drug. Deduplicates by safetyreportid (bug fixed in 0.2.1). Returns total reports, unique reaction count, and top 20 reactions by frequency in the requested window.
| Name | Required | Description | Default |
|---|---|---|---|
| drug | Yes | Generic drug name. | |
| limit | No | ||
| date_to | No | ||
| date_from | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries the burden. It mentions deduplication and a bug fix, plus the returned metrics. This is relatively transparent, though it could note that data is aggregate and not individual reports.
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, no wasted words, front-loaded with purpose. Highly efficient and easy to parse.
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 and only 25% parameter schema coverage. Description explains outputs but omits parameter details. For a simple aggregate tool, it is moderately complete but could be improved by describing parameters.
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 25% (only 'drug' described). The description adds context about requesting a time window but does not specify date format or limit parameters. It partially compensates for 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 it aggregates FDA adverse-event reports (FAERS) for a drug, with specific outputs: total reports, unique reaction count, top 20 reactions. It is distinct from sibling tools (drug approval, label, recall searches).
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 implied usage is for adverse events, but no explicit guidance on when to use or alternatives. It lacks when/not-to-use directions, making it adequate but not outstanding.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct FDA data domain: adverse events, drug approvals, labels, and recalls. No semantic overlap exists between them.
All tools follow a consistent 'fda_<domain>_<action>' pattern, using underscores and clear descriptive names. The two drug-related tools share the 'fda_drug_' prefix.
Four tools are well-suited for the FDA Approvals domain, covering the most common requests (approvals, labels, recalls, adverse events) without being overwhelming.
Core FDA drug information is covered, but clinical trial data or enforcement reports are missing. Agents can work around the minor gap.