Real-user field data

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

Annotations already declare readOnlyHint and openWorldHint, but the description adds real context: it is fast (seconds vs minutes), and crucially that many sites legitimately return NO field data due to Google's traffic/anonymity threshold and that this is not an error — a genuinely useful behavior an agent would otherwise misread as failure. It does not describe the shape of the successful response beyond the p75 series, which keeps it below 5.

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 'Use for...' and then the alternatives, which is the right order. The opening sentence is long and clause-heavy, packing speed, absence of lab data, and two sibling redirects into one breath, but every sentence carries distinct information.

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 two-parameter read-only tool with no output schema, the description covers purpose, alternatives, the history option's meaning, and the important empty-result case. Only the general shape of a successful per-URL response is left implicit, which is a minor gap given the low complexity.

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%, so both parameters are already documented, giving a baseline of 3. The description nonetheless adds interpretation beyond the schema: `history` yields a weekly p75 time series that reveals whether real users have experienced degradation over months, which is more than the schema's 'Also fetch the weekly p75 time series.'

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 (real-user Chrome UX Report field data) and explicitly contrasts it with lab measurement. Names two siblings, analyse_page for lab/fixes and explain_lcp for LCP phase attribution, so an agent can disambiguate without opening any 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 explicit when-to-use (real visitor experience), when-not (lab scores, fixing, LCP diagnostics) and the sibling that covers each alternative. Also states the condition for enabling `history` (wanting to see multi-month slowdown trends).

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