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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, so the safety profile is covered. The description adds genuinely new behavioral context: a 10-40s latency expectation, the 28-day data window, and the source of the field data (real Chrome visitors vs. synthetic Lighthouse). It does not mention failure modes for unreachable URLs, which is the only notable gap.

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?

It is a single tight paragraph that front-loads what the tool returns, then when to use it, then the URL precondition and latency. Every clause carries information, and there is no filler or repetition of the title.

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 must convey return values, and it does: field CWV, a Lighthouse score, and ranked fixes. Latency and data window are also covered. Only the shape of the response (per-URL objects, error handling for failed URLs) is left unstated, which is minor for a read-only diagnostic.

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 100%, so 'urls', 'fixes', and 'strategy' are already documented, including the enum and the max of 5 URLs. The description adds only soft hints ('Any public URL', 'fixes worth most') and gives no detail on the mobile/desktop strategy choice or the per-page fix cap, so it does not exceed 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 names the specific service (Google PageSpeed Insights) and the exact resources it returns: real-visitor Core Web Vitals from Chrome, a Lighthouse score, and prioritized fixes. No sibling tool covers page speed, so this is unmistakably distinct from analytics_landing_pages, search_console_inspect_urls, and the rest.

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 states the trigger ('when clicks don't convert'), names where the URLs should come from ('from landing_page_view or analytics_landing_pages'), and justifies the check via Quality Score. It also sets the input precondition ('Any public URL'), so an agent knows both when to call it and what to pass.

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