audit_pipeline

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

No annotations are provided, so the description carries the full burden. It discloses two key side effects: writing persistent artifacts to a run directory and returning a compact executive summary. However, it does not mention error behavior, reversibility, or resource cost, and 'resilient' is left undefined.

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 sentences with the action sequence front-loaded and no fluff. The core purpose and major outputs are stated efficiently.

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 8 parameters, no output schema, and no annotations, the description gives a high-level overview but omits practical details: what the executive summary contains, how parameters interact, or what happens when pipeline stages fail. For a complex orchestration tool, this is adequate but not thorough.

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 schema covers 75% of parameters, and the description adds no extra meaning to any of them. It doesn't explain how reportMode, minPriority, or projectRoot influence the pipeline, leaving the agent to rely solely on the schema's minimal descriptions.

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 begins with a specific verb ('Run') and resource ('full resilient 0day audit pipeline'), and enumerates the exact stages (Scan → Verify → Chain → Report → Fix). It clearly distinguishes this from sibling tools like scan_file, verify_finding, and chain_findings, which are individual stages.

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 implies this is the comprehensive orchestrator, but it never explicitly states when to use it versus alternatives, nor does it mention exclusions (e.g., 'if you only need a single stage, use scan_file'). The context is clear from the sibling list but not made explicit.

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