harness_audit

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

No annotations exist, so the description carries full burden. It declares itself read-only ('changes nothing, read-only') and lists all specific checks performed, as well as the output format (pass/warn/fail scorecard). This fully discloses 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 description is a single dense paragraph, front-loaded with purpose. It is slightly verbose due to listing many checks, but every sentence adds value. Could be restructured with bullet points for clarity, but remains effective.

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's complexity (many checks), no output schema, and low schema coverage, the description is complete: it specifies all checks, output format, read-only nature, and order of execution. No gaps remain for an agent to invoke 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?

With 0% schema coverage and only one required parameter ('workdir'), the description adds context by mentioning 'reads the session ledger + workdir artifacts', implying workdir is the directory containing these artifacts. This compensates for the lack of schema description.

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 explicitly states it is a governance/process-completeness auditor that reads session ledger and workdir artifacts to check multiple specific conditions. It clearly distinguishes from siblings by noting it should run last after coverage_summary.

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?

The description provides explicit timing: 'Run LAST (after coverage_summary).' It does not include when-not-to-use examples, but the clear placement in the workflow suffices.

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