scan_security

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

Discloses it is read-only, skips test files, and returns JSON with specific fields. No contradiction with 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?

Concise, well-structured, front-loaded with purpose, lists CWEs 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?

Explains return format and SARIF alternative, covers all parameters and annotations, no gaps.

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 100%; description adds value by clarifying defaults (scope whole project, output_format json, severity_threshold low) and special values like ['all'] for rules.

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?

Description clearly states it scans project files for OWASP Top-10 vulnerabilities using pattern matching, lists specific CWEs, and distinguishes from taint_analysis.

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?

Explicitly says use for pattern-based security audit and provides alternative taint_analysis for data-flow-aware analysis.

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