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

With no annotations, the description carries the full burden and does substantial work: it enumerates the measurements taken and the four failure conditions it flags (missing compression, missing Cache-Control, oversized payloads, slow TTFB), and notes the fetch originates "from this server," which matters for interpreting timing. It stops short of disclosing redirect handling, timeouts, or return shape, so it is strong but not exhaustive.

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 sentences, no padding. The primary purpose and metrics lead, and the disambiguation from the sibling tool closes. Each clause adds either scope or routing information.

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?

No output schema and no annotations, so the description must define both behavior and expected results; it does reasonably well by listing the metrics and flags, which effectively previews the output. Gaps remain on redirect following, timeout behavior, and whether the fetch is authenticated, minor for a lightweight probe but not fully covered.

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 100% and there is only a single required url parameter, so the schema already does the work (baseline 3). The description adds one genuinely useful semantic detail beyond the schema — that the measurement is performed from this server, not the caller's environment — which affects how the TTFB figure should be read.

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?

"Fetch a URL and measure time-to-first-byte, total fetch time, and response size" names a concrete verb, resource, and the exact metrics produced. It further differentiates itself from the sibling pagespeed_insights by name, so an agent can route between the two without opening either 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?

Explicitly frames itself as a "lightweight raw-timing check" and states the alternative route: Lighthouse scores, Core Web Vitals, and real-user field data belong to pagespeed_insights. Both the when-to-use and the when-to-use-something-else conditions are present.

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