Start a full-site scan

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

Annotations already indicate the operation is not read-only, is not idempotent, and is not destructive. The description adds valuable behavioral context by disclosing that the tool 'queues the run and returns immediately with a runId,' implying asynchronous execution rather than synchronous completion. This goes beyond the annotations to explain what the agent should actually expect. It does not cover failure modes or then-разрешения, but the queuing behavior is the most important non-obvious trait.

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 description is three sentences with no filler. The core action is first, the asynchronous behavior and polling instruction follow, and the prerequisite condition is last. Every sentence carries functional information and nothing is repeated from the schema or annotations unnecessarily.

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?

For a tool that starts an async job, the description covers the essential flow: initiate, obtain runId, poll with get_run, and precondition (list_sites). It also mentions the Pro+ (SCAN_FULL_SITE) requirement, providing permission context. It could be more complete by stating what happens if the siteHost is invalid or whether scans can be canceled, but those are secondary for a first invocation. Given the lack of an output schema, the runId and polling instructions sufficiently complete the mental model.

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?

The schema description for siteHost is already detailed: it specifies the normalized host, exactly as list_sites reports it, with no scheme or path. The tool description reinforces this by pointing to list_sites as the source for a correct value, which helps the agent avoid constructing the host incorrectly. With 100% schema coverage, the baseline is 3; the explicit list_sites reference adds real guidance on how to obtain the parameter value, pushing it to 4.

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 ('crawls and scans') and a specific resource ('every reachable page of a registered site'). It immediately conveys the action and scope, and the mention of 'every reachable page' distinguishes it from any more targeted scan tool. Though no sibling tools are listed, the purpose is unambiguous on its own.

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?

The description provides explicit sequencing: 'Call list_sites first if you do not already know the exact registered host,' and 'call get_run to poll' after the run is queued. This tells the agent when to use this tool versus its companion tools and clarifies the expected workflow. No ambiguous or missing guidance exists for the primary use case.

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