Page health and failures

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

The annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered; the description adds meaningful context beyond them — scope is limited to the active tab, and results are contaminated by the user's own network, extensions and stored data. It does not say anything about latency, cost, or what happens on restricted pages (chrome:// or unloaded tabs), which is the remaining gap.

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?

Two tight sentences, front-loaded with the concrete list of returned data followed by the caveat that justifies the tool's existence. Nothing is repeated and no filler word survives.

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 read-only, parameterless diagnostic with no output schema, the description covers what is measured, the scope (active tab), and why the data is trustworthy in a way automation is not. It could still mention failure modes — no active tab, restricted URLs, or partial data — to be fully complete.

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?

With zero parameters and 100% schema coverage the baseline is 4, and the description earns it by clarifying the implicit scope: everything returned pertains to the single active tab, not all open tabs. That scoping detail is genuinely additive for a parameterless tool.

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 and resource ('Returns Web Vitals, failed and slow network requests, console errors, storage use and the exact browser environment for the active tab'), enumerating the exact payload so an agent can tell it apart from page-reading siblings like get_page_object or read_page. It falls short of 5 only because it never names an alternative directly; the differentiation is implied by the content list rather than 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 useful implied guidance: the emphasis on 'the user's real session' and 'which a clean automated browser cannot show you' signals this is the tool for real-user measurement rather than synthetic capture. However, it gives no explicit when-not-to-use rule, no mention of prerequisites (an active tab must exist), and no named alternative for cases where a synthetic view is desired.

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