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

Annotations already declare read-only, idempotent, non-destructive behavior. The description adds meaningful behavioral context: it is meant for loose, ambiguous queries and likely presents candidates to choose from rather than performing support validation. This goes beyond what the annotations alone convey.

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?

The description is two concise sentences with the primary purpose first and usage guidance second. Every sentence earns its place; there is no fluff or repetition of schema content.

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?

For a single-parameter, read-only, idempotent tool with an output schema available, the description adequately explains when and how to use it. Nothing critical is missing for an agent to select and invoke it correctly.

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?

The schema already provides 100% parameter description coverage for q, including examples like 'grid' and 'web share'. The description reinforces that the parameter is a loose query but does not add significant new semantics beyond the schema.

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?

The description states a specific verb ('Find'), a clear resource ('caniuse feature id'), and a distinctive mode ('loose query'). It distinguishes from the sibling tools by emphasizing ambiguity, candidate selection, and pre-support-lookup context.

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 description gives an explicit usage condition: use this when a query is ambiguous and candidates need to be chosen before checking support. This also implies when not to use it (unambiguous queries or direct support checks), and the phrase 'before checking support' points toward the sibling check_feature_support.

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