audit_artifact

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

Annotations already provide basic hints (readOnlyHint=false, etc.), but the description adds key behavioral details: supported artifact types (har, lighthouse), that playwright-trace is invalid, and that omitting url_hint causes local IDs that don't cross-reference with live runs.

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 well-structured sentences plus a list – no filler. First sentence states purpose and use cases, second specifies supported types, third gives exclusion. Every sentence adds value.

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?

Given the tool has 3 parameters, an output schema, and annotations, the description covers purpose, usage, parameter details, and behavior completely. It provides all necessary context for correct selection and invocation.

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%, but description adds meaning beyond schema: it clarifies artifact_type enum values (especially that playwright-trace returns error), and explains url_hint's role in cross-referencing findings with audit_url runs.

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 clearly states the tool audits a captured browser artifact (not live URL), with specific use cases like CI debugging and bug reports. It distinguishes from sibling tools like audit_url by focusing on artifacts.

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?

Explicitly says when to use: 'Use for CI-run debugging or customer bug reports without re-running the browser.' It also tells when not to use: 'playwright-trace returns INVALID_PARAMS, use audit_url'. This provides clear guidance.

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