Skip to main content
Glama
Sign In

divux

by si.divux
OverviewDiscussionsAdmin

Pets: pet food recalls and a list of foods and plants toxic to dogs and cats

check_pet
Read-only

Returns FDA animal and veterinary recall notices for a pet food or treat brand or product, newest first, with the reason, the company and the notice link. Also returns a curated list entry for common foods and plants (chocolate, grapes and raisins, xylitol, onions and garlic, macadamia nuts, alcohol, salt, lilies for cats, sago palm, azalea, oleander, tulips, daffodils and more): the source's wording, its page, the date it was read, and poison-control phone numbers (fees may apply). A name that is not on the list has no entry. Applies to questions about pet food recalls, or whether a food or plant is on the list of items toxic to dogs or cats. Results report what the official sources say and are not a safety assessment. Not veterinary advice. Human-food nutrition is outside this result.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "check_pet"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYesA pet food or treat brand or product (e.g. 'Fromm', 'Pedigree wet dog food') or a food or plant name (e.g. 'grapes', 'lily', 'xylitol')
speciesNoThe pet, when known

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior5/5

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

Beyond the readOnly/openWorld annotations, the description discloses negative-result semantics ('A name that is not on the list has no entry'), that poison-control numbers may incur fees, and that output is reported source wording rather than a safety or veterinary assessment. Those are exactly the behavioral caveats an agent needs before relaying results to a user.

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?

The primary recall capability is front-loaded and every sentence carries information, but the closing disclaimers are somewhat redundant ('not a safety assessment' / 'Not veterinary advice') and the single dense paragraph mixes two distinct result types.

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

Completeness5/5

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

There is no output schema, and the description compensates by enumerating the returned fields for both result types (reason, company, notice link; source wording, page, date read, phone numbers). For a two-parameter read-only lookup, nothing an agent needs to call or interpret it is missing.

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?

With 100% schema description coverage the baseline is 3, and the description earns slightly more by framing what the query string is for (a brand/product versus a food/plant name) and by repeating the not-on-list behavior that makes a miss meaningful. It says nothing about the species parameter, however, leaving that to 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?

The description states two concrete capabilities with their resources: FDA animal/veterinary recall notices for pet food brands, and curated list entries for toxic foods and plants. It distinguishes itself from adjacent tools partly by exclusion ('Human-food nutrition is outside this result'), which separates it from check_food, but it never names a sibling directly.

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?

'Applies to questions about pet food recalls, or whether a food or plant is on the list of items toxic to dogs or cats' gives an explicit usage condition. The exclusion of human-food nutrition is a useful boundary, but there is no guidance on when to prefer check_recalls or check_food instead.

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

All divux toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources