audit.prepare

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

With no annotations, the description must disclose behavioral traits. It mentions creating a 'runDir' with artifacts, but does not state if the operation is destructive (e.g., overwrites existing directories), what permissions are required, or whether it modifies external state. The return value is also unspecified.

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 sentence of 13 words, making it concise but lacking structure. It does not front-load critical information nor use bullet points or sections. While brevity is positive, it sacrifices clarity and completeness.

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 6 parameters, no output schema, and no annotations, the description is highly incomplete. It fails to explain the tool's behavior, input usage, output, or side effects, leaving the agent with insufficient information to invoke it 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?

The input schema has 6 parameters with 0% description coverage, yet the tool description provides no information about any parameter (model, tasks, runDir, dispatchMode, failureThreshold, maxFindingsPerTask). The agent has no guidance on how to set these parameters beyond their names.

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 action 'Prepare' and the resource 'audit runDir', listing specific artifacts (TaskCards, prompts, manifest, report dropbox). It effectively distinguishes from sibling tools like audit.run by implying a preparatory step. However, the term 'host-mediated' may be unclear, and the description lacks explicit distinction from other audit-related tools.

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?

No guidance is provided on when to use this tool versus alternatives (e.g., audit.run, audit.collect). The description does not mention prerequisites, context, or any conditions that would indicate appropriate usage.

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