list_captures

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

With no annotations, the description carries the full burden of behavioral disclosure. It does state the return schema (filename, path, size, modified time) and that it lists files in a directory, implying a read-only, non-destructive operation. But it does not reveal whether the search is recursive, how it handles missing/unreadable directories, or sorting order—minor gaps for a listing tool but not critical.

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 efficiently structured: a one-line purpose, then a compact Args section, then a Returns list. Every sentence adds value—no filler, no repetition of the tool name. It front-loads the core function and provides exactly the metadata an agent would need.

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, one purpose), an output schema exists (confirmed by signal), and the description explicitly enumerates all return fields, the description is complete for correct invocation. No additional context is required for an agent to decide to call it and interpret results.

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 description coverage is 0%, so the description must compensate. It does: the 'Args' section explicitly explains that 'directory' is the path to search, giving the parameter purpose and type (string). While it doesn't specify path format (absolute vs relative) or permissions, it fully covers what an agent needs to know to provide the one required parameter.

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 a specific verb ('List') and a concrete resource ('RenderDoc capture files (.rdc) in the specified directory'). It clearly differentiates from siblings like get_buffer_contents or get_draw_calls, which operate on a single capture's internals rather than enumerating files. The scope is unambiguous.

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 clear context—you use this to locate .rdc captures on disk—but it does not explicitly state when NOT to use it or name alternatives (e.g., 'use open_capture to load a specific file'). However, the purpose is so distinct from the siblings that the usage context is effectively self-evident.

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