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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false, so safety is covered; the description goes beyond them with genuinely useful traits: pollAfterMs indicates polling while running, expiresAt explains when a Free scan stops being readable, and the closing line warns that zero blockers is not launch approval. It stops short of auth requirements or what happens for an unknown/expired scanId.

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-loads the core purpose and then orders the returned fields logically (identity/status, then post-completion metrics, then coverage, then interpretation). The first sentence is a dense run-on with many comma-separated clauses, but nearly every clause carries distinct information, so the length is largely earned.

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 carries the full burden of explaining return values and does so thoroughly, including enum values for readiness and effectiveReadiness and the meaning of capped/htmlOnly coverage fields. Only failure modes (invalid or expired scanId) and any auth expectations are unaddressed.

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 100% and the single parameter's schema description already points to scan_site, so the schema does the work. The description adds no format, constraint, or example for scanId, which is the correct baseline when coverage is complete.

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 ('Read one scan') and then enumerates exactly what the record contains: status, target URL, environment, score, readiness, blocker counts, category summaries and coverage. An agent knows precisely what this returns. It does not, however, distinguish itself from the sibling get_scan, leaving a plausible ambiguity unresolved.

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?

Usage is implied by naming the required scanId's provenance ('from scan_site') and by mentioning pollAfterMs for in-flight scans, so an agent can infer this is the detail call for a known scan. But there is no explicit when-to-use/when-not or routing to get_scan/get_finding/list_findings, and no prerequisite or error-condition guidance.

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