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

Annotations already flag this as a safe, idempotent read, but the description adds material the annotations cannot: the status vocabulary (open|partial|announced|none, or unknown when no verified record exists) and the important caveat that recommended_action is a suggestion 'based on public sources, not permission; the website's own terms always take priority'. It also discloses that sources are dated, which tells the agent how to weigh staleness.

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 critical scoping rule ('before acting on a website') is front-loaded, and the return-field inventory at the end is compact. Some density cost comes from the parenthetical acronym list (UCP, ACP, MCP, Visa TAP, A2A) which reads as one very long sentence, but no sentence is dispensable.

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, yet the description still usefully previews the return contract (status, recommended_action, per-action allowances, routes, dated sources) and warns that unknown is a possible answer. What is missing is failure behavior for malformed domains and any guidance on the siblings for batch checks or reporting a wrong record, which would round out routing.

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 parameter with 100% schema coverage, and the schema already documents that it accepts a bare domain or a full URL with an example. The description adds no additional formatting, normalization, or error-handling guidance for the domain argument, so the 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 states a specific verb and resource ('check whether [a website] lets AI agents browse, shop, book or log in') and enumerates the agent-route schemes it inspects. It is unambiguous about scope, though it never names a sibling (e.g. check_domains for batch lookups), so the singular/plural split must be inferred from the tool names alone.

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?

It gives a clear triggering condition up front: call this 'before acting on a website for a user'. That is a genuine when-to-use rule rather than an implied one. However, it offers no explicit exclusions or pointer to check_domains, report_block, or submit_update, so the agent must guess which sibling handles batch checks or corrections.

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