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

Beyond the read-only/idempotent annotations, the description discloses critical behavior: paid per-call billing, a cap of up to 10 notices, and no charge on no-match or stale-data outcomes. These are non-obvious operational facts an agent cannot derive from annotations or schema.

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?

Two tight sentences with pricing and the at-least-one requirement front-loaded, followed by the return shape and billing exception. No wasted text.

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?

With no output schema, the description shoulders return-value explanation and does state up to 10 notices with dates, plus billing outcomes. It could still be richer about the fields each notice contains, but for a search tool it is largely sufficient.

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 coverage is 100%, so the per-field semantics baseline is a 3. The description earns above baseline because the schema marks all five parameters optional, and the description adds the crucial 'give at least one' constraint that the schema does not encode.

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?

States a specific verb (search) against a precisely named resource (Health Canada's published Recalls and Safety Alerts open data) and enumerates the filterable dimensions. This clearly distinguishes it from siblings like search_us_fda_recalls and search_vehicle_recalls_canada.

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 constraint 'give at least one' filter is a genuine usage rule that prevents empty scans. However, it does not explicitly name when to prefer this over alternatives such as search_us_fda_recalls, leaving that to the resource scope.

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