audit_pagespeed

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

With no annotations, the description carries the full burden. It usefully discloses the API-key fallback chain (GOOGLE_API_KEY or PAGESPEED_API_KEY) and the shape of the result, but says nothing about runtime behavior such as audit latency, quota/rate limits, or failure modes when a page is unreachable.

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 opening sentence states the core action, the second lists outputs, and the Args block is compact and scannable. It is slightly padded by enumerating return metrics even though an output schema exists, but nothing is wasted or buried.

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 three-parameter read-style tool with an output schema, the definition covers purpose, all inputs, and credential handling, so an agent can invoke it correctly. What is missing is decision context relative to the sibling CrUX tools and any note on expected latency or error behavior.

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 must carry all parameter meaning, and it largely does: url is documented with a concrete example, strategy lists both accepted values with its default, and api_key explains the optional env-var fallback. The only gap is that the schema has no enum enforcing 'mobile'/'desktop' and the description does not say what happens on an invalid value.

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 opens with a specific verb+resource ("Run a Google PageSpeed Insights lab audit") and scopes it as synthetic Lighthouse data with named metrics, which is enough for an agent to know what it produces. It never names the sibling tools (get_crux_metrics, get_crux_history), so the lab-vs-field distinction is only implied, not stated.

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 routing hint toward or away from the CrUX siblings. The word "synthetic" hints that this differs from real-user field data, but the description never tells an agent which to pick for which question.

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