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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description still adds real behavior beyond that: a hard 20-URL cap per call, robots.txt compliance, and refusal of private addresses (SSRF protection), which materially affects what an agent should pass in. It stops short of describing failure reporting or timeouts for unreachable hosts, which matters given there is no output schema.

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?

A single dense sentence that front-loads the action and limit, then lists return fields in order of importance and ends with the optional quote behavior. No filler and nothing repeated from the schema.

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 output schema, the description takes on the burden of describing return values and does so thoroughly, and both parameters are covered. The remaining gap is error/edge-case behavior — how failed or blocked URLs are surfaced in the response — which an agent calling a network tool would benefit from knowing.

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% — the urls array has no per-property description — so the description must compensate, and it does by fixing the semantics (live fetch, capped at 20, network restrictions apply). For quote it adds meaning beyond the schema's terse 'Text the page should contain' by marking it optional and clarifying the result reports per-page containment.

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?

Specific verb and resource ('check up to 20 URLs live') plus an enumeration of exactly what is returned: HTTP status, redirects, final URL, page title, canonical, and optional quote containment. An agent can distinguish this from validate/verify_citation siblings purely from the description.

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?

Usage is implied by the purpose (verifying live URLs) and the description sets a hard scope of 20 URLs, but it never states when to prefer this over neighbors like validate or verify_citation, nor any when-not conditions. The 'up to 20' ceiling is the only routing signal, so guidance remains inferred rather than explicit.

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