crux

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

Annotations already cover safety (readOnly, idempotent, non-destructive, openWorld), so the description's job is to add context beyond that. It does: a 28-day aggregation window, the possibility of an empty result for low-traffic origins, and the fact that calls are billed. That cost and empty-result disclosure is exactly the kind of thing annotations cannot express.

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?

Three compact fragments with no filler, and the identifying information (what data, what window) comes first. It is telegraphic to the point of omitting a verb, but nothing is wasted.

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 read-only, two-parameter tool with no output schema, the definition covers the data source, the time window, the billing implication and the empty-result risk. What is missing is any explanation of the parameters and of what metrics are actually returned, which leaves the agent guessing at request shape.

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 description coverage is 0%, so the description needed to carry the two parameters and did not. 'origin' is only obliquely implied by 'sites', and 'formFactor' with its PHONE/DESKTOP/TABLET enum and default is never mentioned, leaving a real gap.

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 names a specific resource ('Chrome UX Report 28-day field metrics'), which is informative, but it uses no verb and the tool name 'crux' is an opaque acronym. It does not distinguish itself from the sibling 'pagespeed', which also surfaces performance metrics, so an agent must infer the boundary.

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?

No statement of when to choose this over 'pagespeed' or other siblings. The 'low-traffic sites may have no record' clause signals a failure mode rather than a usage rule, and 'Paid' flags cost but not the conditions under which the cost is justified.

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