psi_analyze

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

There are no annotations, so the description must carry the full burden of behavioral disclosure. It implies a read-only analysis but does not mention what the response contains, whether it performs a live Lighthouse run, whether it returns CrUX field data, or any rate limits/authentication considerations.

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, efficient sentence with no filler and the key API is front-loaded. It is concise, though it sacrifices useful detail; that tradeoff is acceptable for this dimension.

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 annotations and no output schema, the description should explain what the analysis returns, which strategies/categories are supported, and how the output is structured. It does none of this, leaving an agent with only the bare API identity and required schema fields.

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 only 50%: url and strategy have descriptions, but locale and categories do not. The description adds no parameter meaning at all, and the phrase 'page performance' could misleadingly suggest only the PERFORMANCE category is relevant when categories can include accessibility, SEO, PWA, and best practices.

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 a specific verb ('Analyzes'), a clear resource ('page performance'), and the specific API ('PageSpeed Insights API'), which distinguishes it from generic audit tools. It doesn't explicitly contrast with similar siblings like lighthouse_audit or crux_query, but the PSI reference makes the primary function reasonably identifiable.

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?

No usage context or alternative tool guidance is provided. An agent cannot tell when to prefer psi_analyze over lighthouse_audit, crux_query, cwv_report, or seo_meta_analyze, and no exclusions or prerequisites are mentioned.

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