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

Annotations already mark the tool as read-only, and the description adds useful behavioral detail: it calls Google PageSpeed Insights, returns both Lighthouse lab results and CrUX field data, and notes field data is provided only when available. This goes beyond the bare annotation and helps set expectations for incomplete data.

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?

The description is a single well-structured sentence that front-loads the core purpose, names the specific metrics, and then clarifies the data sources. Every clause adds value and there is no filler or repetition.

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?

With no output schema, the description helpfully names the expected output components: LCP, INP, CLS, performance score, Lighthouse lab data, and CrUX field data. It doesn't describe the full response shape or error behavior, but for a simple read-only page-vitals tool, this is sufficient guidance for an agent.

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 both 'url' and 'strategy'. The description does not add new semantic detail about parameters, such as URL formatting or how strategy changes the run. Baseline 3 is appropriate because the schema carries the documentation burden.

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 uses a specific verb ('Get') with a precise resource: Core Web Vitals (LCP, INP, CLS), a performance score, and the data source (Google PageSpeed Insights). It clearly distinguishes this from the sibling site-audit and backlink tools by focusing on page-level vitals and performance.

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 clearly implies when to use the tool: when a page-level performance score and Core Web Vitals are needed, with the added nuance of both lab and field data. It doesn't explicitly name alternatives or exclusions, but the context is clear enough given the unrelated sibling tools.

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