Skip to main content
Glama

Canada recalls & safety alerts (Health Canada, CFIA, Transport Canada)

canada_recalls
Read-only

Search official Canadian recalls and safety alerts for food, health products, medical devices, consumer products, and vehicles by agency, category, class, issue, or date. Check if a product or brand was recalled in Canada.

Instructions

Search Government of Canada recalls and safety alerts from official open data: food (CFIA), consumer products, health products, medical devices and vehicles. Filter by agency, category, recall class, issue, keyword and update-date range. Use it to check whether a product or brand was recalled in Canada, monitor new recalls, or support product-safety and compliance work. Runs the Apify Actor loudtzu/health-canada-recalls on your own Apify account (pay per event: $0.003 per recall notice, billed by Apify; Apify platform usage may apply). Store page: https://apify.com/loudtzu/health-canada-recalls

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": "canada_recalls"
  }
}

Input Schema

NameRequiredDescriptionDefault
issueNoIssue contains. e.g. Listeria, Electrical.
keywordNoTitle/product contains. Case-insensitive.
categoryNoCategory contains. e.g. Food, Car, Household items.
languageNoLanguage. Source feed language.en
maxItemsNoMax results. Newest first.
updatedToNoUpdated on/before. YYYY-MM-DD
runOptionsNoOptional run limits (not passed to the Actor). maxTotalChargeUsd caps what this single call can cost you on Apify.
recallClassNoRecall class contains. e.g. Class 1, Type II.
updatedFromNoUpdated on/after. YYYY-MM-DD
organizationNoOrganization contains. e.g. CFIA, TC, Medical devices, Consumer product safety.
includeArchivedNoInclude archived. Archived notices are excluded by default.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare read-only, open-world, non-destructive, so the safety profile is covered. The description adds genuinely useful context beyond them: it runs on your own Apify account, is billed per recall notice at $0.003, and archived notices are excluded by default. It still says nothing about result ordering/pagination mechanics or rate/error behavior beyond the timeout note that lives 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?

Front-loaded with the resource and coverage scope, then filters, then use cases, then billing. Sentences are dense but purposeful; the trailing store-page URL is the only element that does not help an agent decide or call.

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?

Covers purpose, filter axes, data source and cost, which is substantial for an 11-parameter, zero-required tool. With no output schema, however, the description never indicates what a returned recall record contains, nor what an empty result means, leaving the agent to discover the shape empirically.

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 coverage is 100%, so every parameter including the nested runOptions is already documented, and the description's filter summary (agency, category, recall class, issue, keyword, update-date range) largely restates the schema. The one added signal is the cost-cap framing around runOptions, which is only marginal beyond what the schema text says.

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

Purpose5/5

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

Names a specific verb (Search) and a precisely scoped resource (Government of Canada recalls and safety alerts) with the three issuing bodies and the covered product domains spelled out. An agent can distinguish this from any sibling (charities, permits, store products) without opening the schema.

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?

Gives explicit use cases: verify whether a product or brand was recalled, monitor new recalls, support product-safety and compliance work. It does not name exclusions or alternatives, but the sibling list contains no overlapping recall/safety tool, so there is nothing meaningful to route away from.

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