security_scan

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

With no annotations provided, the description fully discloses behavioral traits: deterministic checks, graph-aware severity elevation, no API key requirement, and return format with attack scenarios and fixes. This is comprehensive and transparent.

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 with a clear opening, bullet points for checks, and explanation of graph-aware severity. It is slightly lengthy but every sentence adds value, though some could be tightened.

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 complexity of a security scan tool with multiple parameters and no output schema, the description covers purpose, check categories, severity logic, and usage examples. It provides enough context for an agent to use the tool correctly.

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%, and the description adds significant value beyond schema by explaining the purpose of 'target' for single-file scans, the default for 'graphAware', and listing all vulnerability classes in detail.

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 'Scan the codebase for security vulnerabilities' and lists specific check categories, distinguishing it from sibling tools like find_dead_code or impact_analysis that focus on other code quality aspects.

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 usage guidance by explaining the --target option for single-file scan and default behavior for graph-aware severity. However, it does not explicitly state when not to use this tool or suggest alternatives among the listed siblings.

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