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

With no annotations, the description carries the full burden and does so: it discloses that this is a live probe making ~6 requests against the target, that it is free, that results depend on a browser control request, and that it can be skipped when the site opted out (optedOut, no requests sent). The full verdict taxonomy (ok/blocked/throttled/degraded/error) and the throttle-vs-block distinction are exactly the kind of behavioral context annotations would otherwise supply.

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?

Front-loaded with the core distinction (observed CDN behavior vs robots.txt), followed by the verdict taxonomy, edge cases, cost, and sibling routing — all load-bearing. Slightly redundant in restating the robots.txt-can't-tell-you point and the parenthetical glosses, but nothing is padding.

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 the result shape; it does so via the verdict vocabulary and the measurable=false case. It stops short of describing the actual response structure (per-crawler mapping, whether bytes/status codes are returned), which is the remaining gap for a tool whose whole value is its output.

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?

One required parameter at 0% schema description coverage; only the JSON Schema pattern hints at the accepted format. The description implies the argument is a bare domain (it probes 'the homepage', not an arbitrary URL), which is useful, but it never states format, scheme handling, or subdomain behavior explicitly.

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?

States a specific action (probe the homepage with each AI crawler's real user-agent and compare against a browser) on a specific resource (a domain's CDN behavior). It explicitly contrasts with the declared policy in robots.txt, which makes it impossible to confuse with the sibling preflight tool.

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?

Ends with an explicit routing rule: 'Use preflight for the declared policy; use this for the observed one.' It also implicitly scopes usage to live probing of a single domain, and the measurable=false explanation tells the agent when the tool yields no verdict rather than a false negative.

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