Audit Project Code

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

Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds context: scans are local, fix fetches require network, and a missing token causes empty results. This provides behavioral insight beyond 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?

The description is concise and well-structured: a summary sentence, a list of categories, ideal use-case examples, and a troubleshooting note. The most important information is front-loaded, with no redundant or unnecessary text.

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 (4 params, no output schema) and strong annotations, the description is complete. It covers the two-step process, categories, defaults, error handling, and typical usage, leaving no significant gaps for an AI agent to invoke 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%, with each parameter described. The description adds practical use-case context for the categories parameter, such as recommended combinations for mobile and web apps, though tokens and maxFiles are not further elaborated.

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 action: 'Scan source files for code issues across 18 categories, then fetch live best-practice fixes from official docs.' It specifies the verb (scan/fetch), resource (source files), and output format (file:line locations), distinguishing it from siblings.

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 when-to-use scenarios, such as using 'all' for broad questions and specific category combos for mobile vs. web apps. It also offers troubleshooting for doc fetch failures. However, it does not compare to sibling tools like gt_search or gt_best_practices, limiting differentiation.

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