Skip to main content
Glama

Vet Product Recalls

vet_product_recalls
Read-onlyIdempotent

Search FDA Enforcement Report recalls for a pet food, animal food, or veterinary drug product or manufacturer. Answers "has Blue Buffalo dog food been recalled", "dog food recalls", "veterinary drug recalls". Source: openFDA food/enforcement.json and drug/enforcement.json, there is no dedicated animal-food recall feed, and coverage of pet-food recalls specifically is uneven (some well-known FDA-confirmed pet-food recalls are not in this dataset at all). A zero-result answer means no FDA Enforcement Report record was found under this name, not that the product was never recalled, check fda.gov/animal-veterinary/safety-health/recalls-withdrawals for the fuller picture the tool states this in its response.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "product": "dog food"
    },
    "name": "vet_product_recalls"
  }
}

Input Schema

NameRequiredDescriptionDefault
lotNoOptional: filter to recalls whose lot/code info mentions this lot number.
kindNoWhich FDA enforcement dataset to search: "food" (pet/animal food, default) or "drug" (veterinary drugs).
limitNoMax recalls to return (1-50, default 10).
productYesProduct name, brand, or manufacturer, e.g. "dog food", "Blue Buffalo", "Bravecto".

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Annotations already cover readOnly/idempotent/openWorld/non-destructive, so the description is free to add what they cannot: the exact upstream sources (food/enforcement.json, drug/enforcement.json), the absence of a dedicated animal-food feed, uneven pet-food coverage, and the crucial semantic that zero results mean 'no record found' rather than 'never recalled'. That is precisely the kind of context structured fields cannot carry.

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

Conciseness3/5

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

The lead sentence is front-loaded and efficient, but the caveat sentence runs long and ends in a garbled clause ('check fda.gov/... the tool states this in its response') that reads as two sentences merged. The valuable coverage warning could be stated more cleanly.

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

Completeness4/5

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

For a two-dataset search tool with no output schema, it supplies source provenance, coverage limitations, and result-interpretation guidance — everything needed to call it and read the answer correctly. Minor gaps like pagination expectations or how 'lot' matching works are left to the schema.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3; the description earns extra by explaining why 'kind' exists — there is no dedicated animal-food recall feed, so pet food is reached through the food enforcement dataset. It does not elaborate on the 'lot' or 'limit' filters, but those are already documented in the schema.

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 and resource ('Search FDA Enforcement Report recalls') plus the exact scope (pet food, animal food, veterinary drug product or manufacturer), and the example queries pin down intent. It stops short of naming which sibling to prefer over the generic 'recall' tool, so an agent must infer that boundary.

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

Usage Guidelines4/5

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

Example questions ('has Blue Buffalo dog food been recalled', 'veterinary drug recalls') give concrete use contexts, and the zero-result caveat tells the agent how to interpret empty output. There is no explicit when-not-to-use or routing to a sibling, which keeps it below a 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.