List code files

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

Annotations already declare readOnlyHint=true. The description adds valuable behaviors: skipping vendor/build directories, depth control, and sandboxing to codeLocation. No contradictions with 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?

Three concise sentences, front-loaded with the core action. Each sentence adds distinct information (action, skips, depth, sandbox). No wasted words.

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?

No output schema, but description mentions returned data (sizes, extensions). For a listing tool with 3 parameters and good annotations, the description covers essential behavior. Sibling tools are numerous but not contradictory.

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 67% with two parameters described. The description reinforces default values for 'depth' and 'subpath' (root). However, the required 'project' parameter lacks description in both schema and description, reducing clarity. Overall, adds moderate value.

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 uses specific verbs ('List') and resources ('files and folders under the project's codeLocation') and adds details like 'with sizes and extensions.' It distinguishes from sibling tools like 'read_code_file' or 'code_file_map' by being a listing operation.

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 mentions skips (vendor/build dirs) and sandboxing, but does not explicitly state when to use this tool versus alternatives like 'code_file_map' or list all files in a project. Implied usage is clear but no direct exclusions or comparisons.

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