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

Annotations only declare readOnlyHint/openWorldHint; the description adds the operationally critical facts: full page render, typical 10–35 s latency, must be run serially, and the user should be told about the wait. These are exactly the behavioral traits an agent needs and that no structured field conveys.

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 what it does and returns, then latency warning, then the sibling routing rule, then the parameter note — a sensible priority order. Slightly dense in the middle, but no sentence is filler.

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 slow, open-world audit tool it covers purpose, latency risk, correct call pattern, alternative tool, and all parameters; the return fields are additionally previewed even though an output schema exists, so nothing operational is missing.

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 0%, so the description carries the burden and does: it enumerates the valid values for strategy ('desktop' oder 'mobile') and explains workspace semantics (customer workspace slug, optional when only one workspace). Only url is left to self-evidence.

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 verb+resource (full Google Lighthouse audit) plus exactly which categories are covered (Performance, Accessibility, Best Practices, SEO). It explicitly contrasts itself with dfs_onpage_instant, so an agent can pick between them without opening a 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 ('the only tool for Core Web Vitals and performance score'), when-not-to-use ('not in loops, not in parallel for many URLs'), and the named alternative for other jobs (dfs_onpage_instant, ~1 s). Nothing is left to inference.

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