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

Annotations only declare this a safe read, so the description carries the rest and does: the full status enum, that failed includes an error explaining causes such as robots.txt blocks, that stalled and progress_pct and next_check_after_s are returned, and where the polling cadence comes from. This is behavior an agent could not infer from the structured fields.

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 purpose and predecessor, then the polling procedure, then the terminal-state outputs. Every sentence adds either a field, a failure semantic, or a required action, and nothing is repeated from annotations or 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?

For a one-parameter polling tool with an output schema available, the description covers the full lifecycle: what to call it after, how often, when to stop, what each terminal state means, and which URLs appear on completion. Nothing an agent needs to drive the loop correctly is missing.

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 0% and the single property carries only the title 'Audit Id', so the description must supply meaning. It does so partly: 'Takes the audit_id' plus 'after start_site_audit' implies the ID comes from the start call, but it never explicitly says the audit_id is the value returned by start_site_audit.

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 verb and resource ('check whether the audit has finished') and explicitly names its sibling start_site_audit as the predecessor. The enumerated return fields (status, pages crawled, report_url) make clear it is a status poller rather than a report fetcher like get_audit_report.

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?

Explicitly says to use it after start_site_audit and gives the full operating loop: show the user the message, then call again after next_check_after_s seconds (20 to 30) until status is completed, failed or canceled. That is when-to-use, cadence, and termination condition all in one place.

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