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

Annotations already cover read-only/idempotent/non-destructive, and the description goes well beyond them: it discloses the exact comparison scope, the notComparableCount fallback for pages a shorter crawl missed, the precise boundary of newIssues, the self-comparison validation error, the failure mode when no baseline exists, and that the call costs no credits.

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 core comparison and the notComparableCount caveat lead, and the error/cost facts are tacked on at the end. It is dense with two nested parentheticals, but each sentence carries distinct information rather than filler.

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 return-value burden and does it: it names the issue categories, notComparableCount, addedUrlCount, and the health-score delta. For a read-only diff tool, nothing an agent needs to call and interpret it 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 description coverage is 100%, and the schema itself already documents auditId, projectId, and the baselineAuditId omission/fallback behavior in detail. The description adds comparison semantics but no parameter-level syntax or format 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?

States a specific verb and resource (compare a site audit against an earlier one) and enumerates the exact outputs: new issues, fixed issues, persisting count, health-score delta. An agent can distinguish this from sibling audit tools (get_audit_core_web_vitals, get_audit_https_report) purely from the description.

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?

Explains the conditions clearly: only pages both crawls visited are compared, an error is returned when no earlier completed audit exists, and it states the tool is free. It does not name an alternative tool to use instead when comparison is impossible, so it stops just short of explicit when-not guidance.

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