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

Annotations already declare read-only and open-world behavior, so the description focuses on valuable extra context: mobile-only data, Chrome UX Report field data at 75th percentile over 28 days, Lighthouse lab metrics, speed opportunities, and a latency caveat of up to a minute. It could still mention failure behavior for invalid or unreachable URLs, but the behavioral profile is well communicated.

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?

Two sentences, front-loaded with the metrics and resource, then the data sources and latency. Every phrase carries useful information and there is no repetition of structured 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 one-parameter read-only tool with no output schema, the description adequately explains what data comes back (field data, lab metrics, opportunities) and how long it may take. It stops short of describing error or fallback behavior when no CrUX data exists, but the essential context is present.

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 the sole parameter's description already explains that it takes a website URL. The description does not add further syntax or constraints beyond the schema, so the baseline 3 is appropriate.

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 names specific metrics (LCP, INP, CLS), the resource (a URL), and the data source (Google PageSpeed Insights mobile). It clearly distinguishes this tool from sibling audits like audit_seo and audit_ai_visibility by focusing on Core Web Vitals.

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?

Usage is implied by the purpose: call this to get Core Web Vitals for a URL. However, there is no explicit guidance on when to prefer this over audit_seo or when not to use it, leaving the agent to infer the boundary.

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