fda_intelligenceSearch FDA data via openFDA: drug approvals, recalls/enforcement and…. Search FDA data via openFDA: drug approvals, recalls/enforcement and adverse-event signals for any drug or company — with an AI summary of the regulatory and…
| Name | Required | Description | Default |
|---|---|---|---|
| input | No | Input for FDA Drug Recalls, Approvals & Adverse Events — openFDA AI. See https://apify.com/noniner/fda-intelligence. |
Changes observed during successful MCP inspections.
Input schema / properties / input / descriptionPrevious value: -"Input for FDA Intelligence — Approvals, Recalls & Adverse Events (AI). See https://apify.com/noniner/fda-intelligence."New value: +"Input for FDA Drug Recalls, Approvals & Adverse Events — openFDA AI. See https://apify.com/noniner/fda-intelligence."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds that results come from openFDA and include an AI-generated summary, which is useful beyond the annotations, but the truncated text never explains what the summary contains, what is returned, or any rate/coverage limits of the openFDA source.
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 text is visibly truncated and duplicated — the same sentence starts twice and both copies end in an ellipsis. Rather than being concise, it is incomplete, and the reader cannot tell what information was lost in the cut-off clauses.
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 a free-form nested input object, no output schema, and a description that breaks off mid-sentence, an agent lacks what it needs to construct a correct call or anticipate the response shape. The key detail — how to specify the drug/company and what the AI summary returns — 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?
Only one optional 'input' object exists and its schema description merely points to an external URL, so the schema itself does not really explain the expected fields. The description hints that a drug or company name is the query subject, which partially fills the gap but gives no field-level guidance for the nested object.
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?
States a clear verb (search) and specific resources (drug approvals, recalls/enforcement, adverse-event signals) via openFDA, plus the AI-summary angle. However, it does not differentiate itself from the nearby sibling clinicaltrials_intelligence, and the sentence is cut off mid-clause twice, leaving the scope of the 'AI summary' undefined.
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?
No indication of when to pick this over alternatives such as clinicaltrials_intelligence, nor any preconditions or exclusions. The only usage framing is 'for any drug or company', which is a scope statement rather than guidance.
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.