audit_task

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

No annotations provided, so description carries full burden. Discloses key behaviors: writes independent-review.md, returns evidence-backed failures, highlights possible heuristic false positives, and separates manual-verification items. Does not mention auth or rate limits, but behavior is well-covered.

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?

Description is concise with front-loaded action ('Independently audit a task's outputs'). Each sentence adds value, though minor redundancy in listing checks could be tightened.

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 task complexity and no output schema, the description sufficiently explains the tool's behavior and output. Covers what is checked and how results are structured, leaving little ambiguity for the agent.

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 has 100% description coverage for the single parameter ('Task ID to audit'). Description adds no further meaning beyond schema; baseline 3 is appropriate.

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 the tool independently audits a task's outputs with specific checks (status, result.md, test.log, etc.) and produces independent-review.md. Distinguishes from siblings like 'diagnose_task' by its comprehensive verification scope.

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?

Describes what the tool does ('Independently audit a task's outputs') but does not explicitly state when to use it over alternatives like 'diagnose_task' or 'safe_audit'. No when-not guidance or prerequisites.

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