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

With no annotations, the description carries the full behavioral burden. It usefully discloses the distinction between lab (Lighthouse) and field (CrUX) data and that field data is conditional, but it says nothing about the external API call's cost, likely 10-30s latency, quota/rate limits, or what happens when a URL is unreachable or unscored.

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?

One dense, front-loaded sentence where every clause names a concrete output (scores, CWV, CrUX, opportunities). The telegraphic fragment style lacks a leading verb, but nothing is wasted.

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 tool with no output schema, the description compensates reasonably by enumerating the return sections an agent would receive. Missing are latency, failure behavior, and usage routing, which are the main remaining gaps for a heavy external-API tool.

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?

There is a single required 'url' parameter with 100% schema description coverage (including an example), so the schema does the work. The description adds only 'for a URL', with no extra detail on format, whether private/local URLs are allowed, or resolution behavior.

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 the exact upstream service (Google PageSpeed Insights) and enumerates what it retrieves: mobile and desktop Lighthouse scores, Core Web Vitals, CrUX field data, and top opportunities. That clearly separates it from routing/content siblings like check_redirects, test_robots, or validate_schema. It stops short of explicitly distinguishing it from the closest sibling, check_rendering, so a 4 rather than a 5.

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?

There is no when-to-use or when-not-to-use guidance, and no alternative tool is named. The one conditional phrase ('CrUX field data when available') describes output conditionality, not invocation choice, so the agent gets no help deciding between this and check_rendering or run_free_audit.

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