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

Annotations already mark it read-only and idempotent; the description adds the key behavioral trait that repeating the call with the same runId is the expected polling mechanism and that a running result must be re-fetched after pollAfterSeconds. It also clarifies the response contains status and, on completion, the report.

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 sentences front-load the action and resource, then immediately give the polling loop. No filler or repetition of schema details.

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 single-parameter retrieval tool with read-only/idempotent annotations, the description provides everything needed to call and poll it correctly: source of runId, expected statuses, wait behavior, and repetition rule. The absence of an output schema is mitigated by the explicit status/report semantics.

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 already explains runId as 'returned by an async tool,' and the description adds value by naming the exact producer tools and stressing that the same runId should be reused across polls. This is more than the schema alone, though the parameter format is already fully documented.

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 uses a specific verb+resource: 'Fetch the status and, when finished, the report for a runId' and ties it to concrete producer tools (check_site_speed, check_ai_visibility, check_local_rank, start_audit). This makes it unmistakable as the async result-retrieval endpoint among the sibling tools.

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 explicitly defines when to call: after an async tool returns a runId, and how to poll: 'wait pollAfterSeconds, then call again with the same runId. Repeat while status is running.' This is actionable and leaves no ambiguity about the call pattern.

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