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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered. The description still adds real value beyond them: the 0-100 output range, that failing checks are returned alongside the score, and that no authentication or account is required. It stops short of saying whether the scan is instant or asynchronous, or whether it incurs cost/rate limits.

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 with zero filler: capability first, output second, access constraint third. Every clause carries information and the key scoping fact (no account needed) is not buried.

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?

An output schema exists, so the description needn't detail return values, and the one-parameter surface is fully specified by the schema. What remains unaddressed is the operational profile — latency, rate limits, and how this differs from run_site_check — which matters for a network-bound openWorld scan.

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?

There is a single required parameter with 100% schema description coverage including an example ("example.com"), so the schema carries the burden fully. The description adds nothing about accepted URL forms (scheme, trailing path, subdomains), so baseline 3 applies.

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 concrete verb and resource — "Score any website 0-100 on how readable it is to AI assistants" — and enumerates the four dimensions measured (crawler access, structured data, discovery files, agent protocols). An agent knows exactly what comes back. However, it never distinguishes itself from the very similar siblings run_site_check and get_site_check, which an agent could easily pick instead.

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?

"Public information only, no account needed" implies the tool works on arbitrary URLs not yet added via add_site, which is useful usage context. But there is no explicit statement of when to use this versus run_site_check/get_site_check, and no exclusion or prerequisite guidance despite three plausibly overlapping siblings.

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