scan_codebase

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

With no annotations provided, the description carries the full burden. It discloses behavioral traits like 'real-time vulnerability database lookups', 'AI reasoning and confidence scores', and the six analysis categories, which helps understand the tool's scope. However, it doesn't mention performance characteristics, rate limits, authentication requirements, or what happens during scanning (e.g., whether it modifies files).

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 bullet points for analysis categories and return values, making it easy to scan. It's appropriately sized at 10 sentences, though some phrasing like 'AI-powered security audit' could be more precise. Every sentence adds value, but minor redundancy exists (e.g., listing categories in both text and bullets).

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 no annotations and no output schema, the description provides good coverage of what the tool does and returns (findings with severity, reasoning, references, remediation). However, for a complex security tool with 4 parameters, it lacks details on error handling, performance, or integration constraints, leaving some contextual 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 description coverage is 100%, so the schema already documents all four parameters thoroughly. The description doesn't add any parameter-specific information beyond what's in the schema, such as explaining the relationship between 'path' and 'files' alternatives or providing examples. Baseline 3 is appropriate when the schema does the heavy lifting.

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 an 'AI-powered security audit' with 'real-time vulnerability database lookups', specifying it 'analyzes code for' six specific vulnerability categories. It distinguishes from the sibling 'check_dependencies' by covering a broader scope including authentication, API security, secrets, and data flow issues, not just dependencies.

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 implies usage for security scanning of codebases but doesn't explicitly state when to use this tool versus the sibling 'check_dependencies'. It mentions 'alternative to path' for the files parameter, which provides some contextual guidance, but lacks explicit when/when-not rules or clear alternatives.

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