list_captures

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

No annotations exist, so the description carries the full burden. It correctly states that it returns a list of capture files with metadata (filename, path, size, time). However, it does not disclose whether subdirectories are searched, what happens if the directory is invalid or empty, or if there are performance considerations. The return format is partially described.

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 fairly concise with a clear summary, an Args section, and a Returns section. It is well-structured and easy to read. A slight improvement could be merging the Args and Returns into a more compact form.

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 simplicity (one parameter, no annotations, output schema exists), the description is mostly complete. It lists the return metadata fields. However, it could mention default behavior (e.g., non-recursive, sorted by name) and error handling.

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 only parameter 'directory' is defined in the schema as a string with no description. The tool description adds: 'The directory path to search for capture files.' This clearly explains the parameter's role and expected input, adding significant meaning 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 'List all RenderDoc capture files (.rdc) in the specified directory.' It uses a specific verb 'List', identifies the resource 'capture files', and specifies the scope (in a directory). This distinguishes it from sibling tools, which focus on other aspects like draws, buffers, or pipeline state.

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 does not provide explicit guidance on when to use this tool versus alternatives. It is implied by the tool's name and purpose that it is for listing captures, but there is no mention of when not to use it or what prerequisites exist (e.g., directory must exist).

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