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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds genuinely useful behavior context beyond them: robots.txt is respected, the run is unthrottled and lab-based, and it is a paid x402 call at $0.001 — the cost/auth detail is important for an agent deciding whether to invoke it.

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-loads the resource and method, then compresses metrics into a single dense clause. Every sentence carries information (metrics, methodology, cost, robots), though the metric enumeration is slightly dense.

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 carries the burden of describing returns — it does list the metrics and rating bands (good/needs-improvement/poor). With annotations covering the read-only nature and cost/robots disclosed, this is nearly complete, short only of pagination or response shape details.

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 100% and both parameters (url, device enum) are already documented in the schema. The description mentions 'mobile or desktop' but adds no syntax or format detail beyond what the schema provides, 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 resource (page speed / Core Web Vitals) and the exact method (real headless-Chromium load) plus the metrics returned. It proactively distinguishes itself from adjacent approaches by stating 'not Lighthouse, not field data', so an agent can identify it 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?

The description clarifies the measurement methodology (lab run, unthrottled, Cloudflare network) which aids selection, but it never states when to prefer this over siblings like site_audit or site_metadata. Usage is implied rather than routed.

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