Code Audit

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is known. The description adds valuable behavioral context beyond annotations: it explains that Semgrep hits are filed as CANDIDATE findings (not exploits) and that gitleaks hits are redacted and kept only in the deliverable, not as findings. It also details the output files. This enriches the agent's understanding without contradicting annotations.

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 well-structured and front-loaded with the core action, followed by concise bullets and clarifying notes. It avoids fluff—every sentence adds either behavioral detail, parameter context, or usage guidance. The formatting (code blocks, bullets) makes it scannable.

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 presence of an output schema (not shown but indicated), the description sufficiently covers what an agent needs: it explains the tool's inputs (path), outputs (two files with their formats), the distinction between findings and candidates, and the prerequisite for using it (source_fetch). It also addresses the no-source case. This is comprehensive for a read-only audit tool with clear annotations.

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 0%, so the description carries the burden. It explains the 'path' parameter (relative to workspace, default 'source') and its relationship to source_fetch, but does not mention 'wait_seconds' at all. Since wait_seconds is a numeric parameter with a default, its purpose is inferable, but the description adds no explicit meaning. Partially compensates but leaves one parameter unexplained.

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's purpose: 'Run the white-box code audit over source in the engagement workspace.' It specifies the exact resource (source code) and the two scanning tools (Semgrep and gitleaks), and differentiates itself from siblings like semgrep_scan and secret_scan by describing a merged audit deliverable. The verb 'run' and resource 'white-box code audit' make it unambiguous.

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 usage guidance: it instructs the agent to run source_fetch first if no source exists, and to confirm repository ownership. It also clarifies what the tool does NOT do (unvalidated gitleaks regex matches are not findings), preventing misuse. This exceeds basic when-to-use guidance by naming a prerequisite and exclusion.

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