audit_repo

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

Annotations indicate non-destructive behavior (readOnlyHint=false, destructiveHint=false). The description adds context by specifying it is a static scan and lists types of issues detected. While it does not detail side effects, the nature of a static scan is non-mutating, and annotations already cover safety.

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 concise (two sentences), front-loaded with the core purpose, and includes a sibling distinction. Every sentence adds value without redundancy.

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 existence of an output schema (as indicated by context signals) and the clear parameter documentation, the description is complete. It explains the tool's role, what it detects, and when to use an alternative, fully covering needed 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 descriptions cover all parameters (100% coverage), providing adequate documentation. The tool description does not add further meaning beyond the schema; it reiterates the tool's purpose but does not enhance parameter understanding.

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's purpose: 'Static UX + a11y scan of a local codebase tree' and lists specific detections (missing alt text, unlabeled elements). It also distinguishes from sibling 'audit_url' for live pages.

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 explicitly advises when not to use this tool ('For live pages use audit_url'), providing a clear alternative. It implies usage for local codebase scanning.

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