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

Annotations already cover the safety profile, and the description adds useful behavioral context: it is free, asynchronous, yields a runId and pollAfterSeconds, and cached results skip polling. No contradiction with readOnlyHint or idempotentHint exists.

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 short sentences front-load the core action and then give the essential workflow. Every sentence earns its place, and there is no redundant or filler wording.

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 one-parameter asynchronous tool with no output schema, the description supplies the lifecycle details needed to use it correctly: runId, pollAfterSeconds, status polling, and cached-result behavior.

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 covers the only parameter, url, completely with guidance about the scheme. The description adds no extra parameter-level semantics, so the baseline 3 is appropriate.

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 verb and resource: 'Start a Google PageSpeed run (mobile and desktop) for a website.' This clearly separates it from retrieval siblings like get_audit_report and implies a distinct role from start_audit.

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?

It provides a clear follow-up workflow: wait pollAfterSeconds, call get_audit_report with runId, and poll while status is running. The caching note adds an explicit condition, though it does not directly compare against sibling tools beyond get_audit_report.

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