PageSpeed Insights

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

With readOnlyHint and openWorldHint already declared, the description adds real context beyond the annotations: an expected latency of 10–40 seconds and the caveat that CrUX field data only appears when there is enough real-user traffic. It does not discuss quota or error behavior, but the latency disclosure is exactly the kind of operational detail an agent needs.

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 core sentence is front-loaded with the verb and resource, and the follow-on enumeration of return contents is dense but each item is informative rather than filler. The separate one-line latency note is short and useful. Slightly long as a single sentence, but nothing reads as waste.

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?

There is no output schema, so the description must describe return values and it does so thoroughly, including the conditional nature of CrUX data. Annotations cover the read-only safety profile. The remaining incompleteness is the untouched strategy parameter and the lack of sibling routing.

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 must carry the full parameter burden, and it largely does not. The strategy parameter (mobile/desktop, defaulting to mobile) is never mentioned at all, which is a meaningful omission since it materially changes results; the categories parameter is only indirectly gestured at via the phrase "category scores" and "SEO/accessibility/best-practice audits."

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 and resource ("Runs PageSpeed Insights (Lighthouse) for a URL") and enumerates the concrete outputs: category scores, CrUX field data, lab metrics, opportunities, failing audits. It does not explicitly differentiate itself from plausibly overlapping siblings such as audit_page or page_performance, so the 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?

Usage is implied by the name and the described output set, but there is no explicit when-to-use, when-not-to-use, or alternative routing against audit_page/page_performance. The only qualifying condition given ("when there is enough traffic") concerns CrUX data availability, not whether to call the tool.

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