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

Goes well beyond the readOnlyHint/openWorldHint annotations: run latency of 10-40 seconds, one-hour caching, 503 as the busy-quota failure mode, a $0.005 USDC charge per successful call via x402, and the fact that failed calls are not charged. This is exactly the operational detail an agent needs before committing to a paid, slow 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 purpose, then cost/latency/failure information in tight sentences with no filler. The enumeration of returned artifacts is somewhat redundant given an output schema exists, costing it a point.

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 paid, slow, external-quota tool, the description covers cost, latency, caching, failure mode, defaults, and scope. With an output schema present it need not explain return structure, and nothing an agent needs before invoking is missing.

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 the schema already documents url, strategy, and categories including defaults. The description only echoes 'Mobile by default' rather than adding format, constraint, or interaction detail, so the baseline 3 applies.

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+resource ('Google PageSpeed Insights for one public URL') and enumerates exactly what it returns: Lighthouse scores, lab Core Web Vitals, CrUX field data, and top five opportunities. An agent can distinguish it from adjacent siblings like audit, headers, or ssl without opening the 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 usable operating context ('one public URL', 'Mobile by default', keyless quota sharing), which implies when the tool applies. However, it never names an alternative or a when-not condition, so the agent must infer the boundary against siblings like audit or headers itself.

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