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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, but the description adds substantial behavior beyond them: polling cadence via pollAfterSeconds, error backoff via retryAfter, handling of unknown/incomplete/failed scan states, and an explicit caveat against interpreting categories as confirmed tracking. It also bounds scope by excluding page settings, scan-wide network signals, and accept/reject behavior.

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 purpose and returned data are front-loaded, followed by caveats and polling mechanics. Every sentence carries information, though the caveat block is dense and could be tightened into fewer clauses without losing meaning.

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?

With no output schema, the description takes on the burden of explaining what comes back and does so field by field. It also covers async polling behavior, error retry signals, and the interpretive limits of partial or failed scans, which is everything an agent needs to call and read this correctly.

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 at 100% schema description coverage, and the description's reference to 'the scanId returned by start_quickscan' merely restates the schema text. No additional syntax, format, or edge-case meaning is added beyond the schema, so the baseline of 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?

Uses a specific verb ('retrieve') plus the exact returned payload: progress or sanitized findings, banner provider and controls, CookieRisk score, pre-consent tracking status, classifications, initiator hosts and consent signals. It also delineates scope by noting page settings and scan-wide network signals live elsewhere, which lets an agent distinguish this read from its sibling start_quickscan. The only shortfall is that the sibling relationship is framed purely as a producer/consumer link rather than an explicit alternative.

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?

Clearly states to use the scanId from start_quickscan, and gives concrete operational instructions: observe pollAfterSeconds before polling and retryAfter on an error. It also states what the result does NOT prove (a tracking category alone is not confirmation; unknown/incomplete/failed scans don't establish absence) and that accept/reject behavior is out of scope. No explicit when-not-to-call-this-tool statement beyond those scope exclusions.

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