run_security_audit

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

With no annotations provided, the description carries the full burden of disclosing behavioral traits. It only states that it runs audits and returns a report, but does not mention whether this involves network access, modifies any files, requires specific project setup, or what the 'structured vulnerability report' contains in terms of format or fields. This is insufficient for a tool that executes external commands, as the agent may need to know about side effects or constraints.

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, front-loaded sentence that immediately states the action and the specific audits run, followed by the return type. There is no superfluous information, and it is appropriately sized for the tool's simplicity.

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?

For a tool with one optional parameter and no output schema, the description is largely adequate. It lists the audit commands and mentions the structured report, which gives the agent a good idea of what to expect. The only minor gap is that it does not explicitly mention that it operates on the given project path or how the path is used, but this is implied by the parameter. Overall, it covers the essentials.

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 already documents the single parameter (project_path) with a clear description. The tool description does not add any additional meaning beyond what the schema provides, such as default behavior or path format expectations. Since schema coverage is 100%, the baseline score of 3 applies.

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 runs dependency security vulnerability audits and lists the specific underlying tools (npm audit, cargo audit, pip-audit). It also specifies the return type (structured vulnerability report), making it distinct from siblings like run_checks or run_tests. The verb 'audit' and resource 'dependency security vulnerabilities' are concrete and 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 gives no guidance on when to use this tool versus the sibling tools. It does not mention prerequisites, when a security audit is appropriate, or whether to prefer this over run_checks or run_staged_checks. The context is completely absent, leaving the agent to infer the intended use case.

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