web_vitals

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

Beyond annotations (readOnlyHint, idempotentHint, destructiveHint), the description adds critical behavioral context: requiring pre-load instrumentation, reporting hook status instead of returning zeros if not installed, and scoping to user-perceived stability after load. No contradiction with annotations.

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 concise at 4 sentences, front-loading the key metrics in the first sentence, then covering prerequisites and scope. Every sentence adds unique value without redundancy.

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?

Given the tool has one optional parameter, no output schema, and comprehensive annotations, the description sufficiently covers what the tool returns, its prerequisites, and what it does not cover. No gaps are apparent.

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?

The single parameter tab_id is fully described in the schema (100% coverage), and the description adds no additional meaning beyond what the schema provides. Baseline 3 is appropriate.

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 clearly states that it retrieves Core Web Vitals (CLS, LCP, FCP, TTFB, long tasks, INP approximation) accumulated since document load. It distinguishes itself by noting it covers user-perceived stability and responsiveness after load, not load timings, differentiating from siblings like get_performance.

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?

The description explains the prerequisite that page instrumentation must be active from before load (installed via navigate()), and that it reports whether it was hooked. It clarifies the scope (post-load) and implicitly suggests other tools for load timings, but does not explicitly name alternative tools for when not to use this tool.

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