Skip to main content
Glama

search_drug_recalls

Search FDA drug recall and enforcement reports by company, classification (I-III), status, state, or date range to assess recall severity and scope.

Instructions

Search FDA drug recall and enforcement reports. Find recalls by company, classification (I-III), status, state, and date range. Class I is most serious (may cause death), Class III is least serious.

Tool call template

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": "search_drug_recalls"
  }
}

Input Schema

NameRequiredDescriptionDefault
skipNoNumber of results to skip for pagination
limitNoMaximum results to return (1-100, default 10)
stateNoUS state code (e.g., 'CA', 'NY')
dateToNoEnd date (YYYY-MM-DD or YYYYMMDD format)
statusNoRecall status
dateFromNoStart date (YYYY-MM-DD or YYYYMMDD format)
recallingFirmNoName of the recalling company
classificationNoRecall classification (I=most serious, III=least)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.2.2
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  2. First observedv1.2.0

TDQS

B3.2/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the full burden, and it discloses almost nothing behavioral: no default result ordering, no pagination/result-volume expectations, no indication of which recall fields are returned, and no note on whether enforcement reports and recall records are merged. The classification-severity sentence adds domain context, but it largely duplicates the enum description already in the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three compact sentences, front-loaded with the resource and then the filter surface, with no filler. The final classification sentence is slightly redundant with the schema's enum description, which keeps it from a 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

All parameters are optional and individually documented, so the description is sufficient to attempt a call. However, with no annotations and no output schema, the definition leaves gaps an agent would plausibly need: result shape, ordering, and how broadly a no-filter search behaves.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and every one of the 8 parameters, including enums, pagination bounds, and date formats, is already documented in the schema. The description restates the filter set but adds no format, matching, or precedence guidance beyond what the structured fields supply, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Search') and a precisely scoped resource ('FDA drug recall and enforcement reports'), and the enumerated filter dimensions reinforce that scope. It does not explicitly contrast itself with siblings like search_device_recalls or search_drug_adverse_events, but the resource noun itself ('drug recall') is distinct enough that an agent can separate them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The second sentence lists what can be filtered on, which implies 'use this to find recalls matching these criteria', but there is no explicit when-to-use framing, no note that all filters are optional, and no routing to alternatives for device recalls or adverse events. Usage is inferable rather than stated.

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