psi_audit

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

Goes well beyond the readOnlyHint/openWorldHint annotations by disclosing the 30-90s latency, the anonymous-quota rate-limit behavior (HTTP 429), the required PAGESPEED_API_KEY, and the conditional nature of CrUX data (only returned when Chrome has sufficient real-user traffic). These are exactly the operational facts an agent needs before scheduling a call.

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?

Front-loaded with the one-line purpose, then budget/auth caveats, then Args and Returns in tight blocks – no filler sentences. The Returns block partially duplicates the declared output schema, but it earns some of its space by noting the CrUX field data is conditional on real-user traffic.

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?

Covers everything needed to call this correctly: the target resource, latency, auth/quota caveat, all three parameter semantics with defaults and enums, and a summary of what comes back. With an output schema present it need not spell out the return shape, and it still gives a useful high-level view.

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 coverage is 0%, so the description must carry the parameters, and it does: url as an absolute public URL with a concrete example, strategy with its 'mobile' default and 'desktop' option, and categories as a subset of four named values defaulting to all four. This supplies the enum values, defaults, and format constraints that the bare schema omits.

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 (Run audit) and resource (PageSpeed Insights on a public URL) and unpacks what the audit composes: 'Lighthouse lab test + CrUX field data.' The lab+field composition implicitly distinguishes it from the sibling psi_field_data_only without the agent needing to open either schema.

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?

Gives clear context for use: a public URL, a 30-90 second runtime, and the prerequisite that a PAGESPEED_API_KEY is needed for regular use because the anonymous quota returns 429s. It stops short of explicitly naming psi_field_data_only as the lighter alternative when the agent only wants field data, so the when-not case is left to inference.

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