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

With no annotations, the description carries the burden, and it does disclose meaningful behavior: it makes an external call to Google, works without an API key at low volume, and requires a server-side key for higher throughput. It also caveats that field data is included only 'where available.' It does not discuss error behavior or side-effect safety explicitly, but the read-only nature is implied by the described read operation.

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?

Three sentences, front-loaded with the core purpose and outputs, followed by the authoritative positioning and auth/rate guidance. Every sentence adds value and none duplicate schema fields.

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 simple two-parameter read-only tool with no output schema, the description covers what it returns, the external dependency, key/rate behavior, and field-data caveat. It lacks explicit error/failure semantics, but an agent has enough to select and invoke it correctly.

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 baseline applies. The description mentions a URL and field data but adds no parameter-level meaning beyond the schema, and it does not elaborate on strategy defaults or constraints.

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 opens with a specific action and resource: running Google's PageSpeed Insights (Lighthouse + CrUX) against a URL, and it lists concrete outputs (performance score, Core Web Vitals, field data). It also distinguishes itself as the authoritative counterpart to a local timing check, which helps separate it from nearby performance tools.

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 communicates when to prefer this tool ('Authoritative version of a local timing check — hits Google's own infrastructure') and gives operational guidance about API-key requirements and throughput. It stops short of naming explicit alternatives or when-not-to-use conditions, so it is clear but not fully exclusionary.

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