security_audit

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

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions the tool 'SAVES: Claude context for strategic decisions' which hints at statefulness or caching behavior, but doesn't describe what the tool actually returns (results format, severity levels, recommendations), performance characteristics, error conditions, or authentication requirements. For a complex security analysis tool with 12 parameters, this leaves significant behavioral gaps.

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 uses a bullet-point structure with WORKFLOW, TIP, and SAVES sections which improves readability, but contains redundant elements. 'Perfect for understanding complex code, identifying issues, and technical debt assessment' repeats the purpose rather than adding new information. The TIP section provides workflow advice but could be more concise. Overall, some sentences don't earn their place in a tool description.

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 complex security analysis tool with 12 parameters, no annotations, and no output schema, the description is incomplete. It doesn't explain what the tool returns (critical for an analysis tool), doesn't describe error handling or performance expectations, and provides minimal guidance on parameter selection despite the many options. The mention of saving context is helpful but insufficient to compensate for the missing behavioral context.

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 description coverage is 100%, so the schema already documents all 12 parameters thoroughly with descriptions, defaults, and enums. The description adds no specific parameter information beyond the general mention of 'analyzing data flows, authentication chains, and cross-file vulnerabilities with OWASP compliance checking' which loosely maps to some parameters like 'focusAreas' and 'includeOwasp'. This meets the baseline for high schema coverage but doesn't add meaningful value beyond the schema.

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 performs a 'comprehensive security audit across entire project' with specific analysis areas (data flows, authentication chains, cross-file vulnerabilities, OWASP compliance). It distinguishes from siblings like 'analyze_single_file' by emphasizing cross-file analysis and project-wide scope. However, it doesn't explicitly differentiate from 'analyze_wordpress_security' or 'audit_wordpress_plugin' which might have overlapping security focus.

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 some usage context with 'WORKFLOW: Perfect for understanding complex code, identifying issues, and technical debt assessment' and 'TIP: Use Desktop Commander to read files, then pass content here for analysis.' This implies when to use it (complex code analysis) and suggests a workflow, but doesn't explicitly state when NOT to use it or mention specific alternatives among the many sibling tools for simpler analyses.

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