list_directory

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

Annotations declare readOnlyHint=true, which is consistent with listing. The description adds that it returns metadata including MIME/type, conversion support, and relative path, and that depth and glob filtering are supported. However, it doesn't disclose the default limits (limit=150, max_depth=2), the sandboxing behavior, or whether pattern matches are case-sensitive. Some behavioral context is present but not rich.

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?

Two sentences, front-loaded with the main purpose. It's concise and avoids repetition. The second sentence lists return details and capabilities efficiently.

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?

An output schema exists, so return values needn't be explained, but the description already spends a sentence on them. More critically, with 7 undocumented parameters and no usage guidance, the description is insufficient for correct invocation. It does not cover the default workspace or how to filter, which are essential for correct use.

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 0% – none of the 7 parameters are described in the schema. The description mentions 'depth' (max_depth) and 'glob filtering' (pattern), but leaves rel_path, workspace, limit, include_dirs, and include_files completely undocumented. The description fails to compensate for the low schema coverage, which is critical for a tool with 7 parameters.

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?

States a specific verb (Explore/List) and resource (sandboxed filesystem tree), and clarifies the return content. The scope 'sandboxed filesystem tree' distinguishes it somewhat from read_file/read_file_markdown, but the description does not explicitly differentiate from siblings like grep_search or read_files_batch.

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?

No when-to-use guidance. It doesn't say whether to use this instead of read_file/grep_search to discover paths, nor does it mention prerequisites like needing a valid workspace. The mention of 'depth and glob filtering' implies use cases but provides no selection criteria.

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