US FDA open data: drug adverse events, drug/food/device recalls, drug labels.
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "fda_lookup"
}
}| Name | Required | Description | Default |
|---|---|---|---|
| q | No | Optional search query, e.g. aspirin. | |
| kind | No | Dataset. | drug/event |
| limit | No | Max results (default 5). |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. 'Open data' hints that no auth is required and the tool is read-only, but nothing states rate limits, whether the default dataset is returned when kind is omitted, or what a call returns. For a zero-annotation tool this is a thin disclosure.
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?
A single front-loaded fragment with zero padding, listing the highest-value information first. It is dense but lacks any sentence structure or scoping detail, keeping it just below the top score.
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?
With no annotations and no output schema, the description should disclose the return format and the effect of defaulting kind to drug/event, but it does neither. The dataset coverage is complete, yet the agent is left guessing about response shape and result-size behavior.
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 the baseline is 3. The description does add some meaning by decoding the terse enum values ('drug/event' = adverse events, '*_enforcement' = recalls, 'drug/label' = labels), but it says nothing about q semantics or the limit parameter, so it does not clearly exceed 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 names the data source (US FDA open data) and enumerates the specific dataset domains it covers — adverse events, recalls, labels — which tells an agent exactly what resource it reaches. It omits an explicit verb (lookup/query), but the name plus the dataset enumeration makes the operation unambiguous and none of the siblings (dns_lookup, crypto_price, wikipedia_summary) overlap.
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?
There is no statement of when to use this tool, no prerequisites, and no guidance against alternatives such as web_read or wikipedia_summary for health/recall questions. The only implicit cue is the data-domain list, which the agent must infer from.
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.