Audit Project Code

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

The description adds significant behavioral context beyond annotations (readOnlyHint, idempotentHint, etc.). It discloses that audit patterns run locally while fix guidance fetch requires network, explains the output format (file:line locations), and details the parameters' impact. Authentication needs are addressed with the GitHub token hint.

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 sentence defining purpose, followed by category enumeration, usage guidance, and troubleshooting. It is appropriately sized for the information density, though it could be slightly more concise without losing substance.

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 tool's complexity (multiple categories, network dependency, no output schema), the description covers essential aspects: what it does, output format, category combinations, failure mode, and authentication requirements. It is sufficiently complete for an agent to use the tool effectively.

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?

The input schema has 100% coverage with descriptions, and the tool description further enriches parameter meaning. It lists all category options and provides concrete usage patterns (e.g., for broad questions or mobile apps). Additionally, it explains the tokens and maxFiles parameters' defaults and ranges, adding 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's function: 'Scan source files for code issues across 18 categories, then fetch live best-practice fixes from official docs.' It specifies the resource (source files) and action (audit with fix retrieval), differentiating it from sibling tools like gt_auto_scan or gt_batch_resolve by its focus on both issue detection and fix guidance.

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 explicit usage scenarios: use 'all' for broad questions, specific category combinations for mobile apps (e.g., ['mobile', 'react', 'typescript']) and web apps (e.g., ['react', 'nextjs', 'typescript']). It also addresses when doc fetches fail (set GT_GITHUB_TOKEN). Although it doesn't directly compare to sibling tools, the context is clear.

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