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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is clear. The description adds valuable behavior: sorting by severity, inclusion of severity/status summaries, per-website tracker spanning audits rather than per-run count, and the persistence model of issues staying open until re-checked. It also explains why counts differ from related tools.

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 description is longer than average but every section earns its place: it explains the bug-tracker analogy, sorting/summaries, the crucial per-website vs per-run distinction, and routing to siblings. It is front-loaded with the core purpose and saves the numerical caveat for the end. Could tighten slightly, but it's dense and mostly necessary.

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?

Comprehensive for a read-only list tool: it explains return summaries, sorting, filtering, the relationship to get_issue, and the critical caveat about count comparability. No output schema exists, so the description appropriately explains what the response contains and why.

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%, so the schema documents all six parameters with descriptions and enums. The description adds context on filtering by status/severity/category and how pagination works through limit/offset defaults, though the schema already covers those details. There's a small bonus for explaining the issue-number link to get_issue.

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?

Clearly states it lists a website's open audit issues, compares them to a bug tracker, and specifies each issue is one failing rule with occurrences across pages numbered per website. Distinguishes itself from sibling tools like list_audits, get_issue, and run_audit.

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?

Provides explicit guidance on when to use this tool vs alternatives: use issue numbers with get_issue for details, compare runs with health_score from list_audits, and notes that open counts are not comparable to list_audits or report failed/warnings. This is strong alternative-routing.

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