FDA recall search (openFDA) — Search US FDA enforcement recalls for drugs, food, or devices by free-text query. Source: openFDA. JSON. Price: $0.005 USDC (Base, via x402).
| Name | Required | Description | Default |
|---|---|---|---|
| q | Yes | search terms | |
| type | Yes | drug | food | device | |
| limit | No | 1-25 (default 5) |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark it read-only and open-world. The description adds useful behavioral context beyond annotations: the source is openFDA, the result format is JSON, and there is a specific per-call price. It does not cover rate limits or response shape, but the read-only nature lowers the burden.
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 short and front-loaded with the core purpose, then adds source, format, and price. There is minor redundancy among 'FDA recall search', 'Search US FDA enforcement recalls', and 'Source: openFDA', but overall every sentence contributes useful information.
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 simple read-only tool with three parameters and no output schema, the description covers the query scope, categories, source, output format, and cost. It does not describe the exact response structure, but that is not essential for correct invocation.
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 schema already explains q, type, and limit. The description lightly reinforces q as a free-text query and names the type values, but it does not add substantive meaning 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 uses a specific verb ('Search') with a precise resource ('US FDA enforcement recalls') and the categories drugs, food, and devices. This clearly distinguishes it from sibling tools like fda_drug_label because it targets recalls, not labels.
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 gives clear context: use it for FDA enforcement recall lookups across drug/food/device categories. It does not explicitly name sibling alternatives or state when not to use it, so it stops short of a full 5.
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.
Many tools are clearly separated by prefix and data source, but several bundled products overlap heavily: vehicle_deal_check vs vehicle_report, realestate_property_report vs realestate_site_risk, finance_company_360 vs finance_health_scan, and domain_due_diligence vs email_domain_check/business_vet. An agent would frequently struggle to pick the correct premium bundle.
Tool names overwhelmingly follow a consistent snake_case category-prefix pattern like weather_, crypto_, vehicle_, finance_, and geo_. Minor deviations such as bare names (domain, ip) and noun-verb forms (dns_lookup, url_check) are easy to learn and don't create real confusion.
50 tools is far beyond the typical well-scoped 3–15 range and will require heavy filtering to navigate. The broad multi-domain data marketplace partially justifies the size, but it would be more coherent split into per-domain servers or consolidated further.
For a read-only data/diligence marketplace, the surface is quite comprehensive: weather, vehicle, crypto, SEC/finance, domain/email, sanctions, and geo workflows all have core operations plus fused verdict bundles. Minor gaps exist—such as a simple crypto price lookup or vehicle market value—but agents can usually work around them.