List Files in Directory

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, covering the safety profile. The description adds the non-recursion behavior, which is not covered by annotations. However, it does not disclose details like pagination behavior, response format, or any potential errors. For a read-only operation with annotations, the description adds modest incremental value but could be richer (e.g., mention that the result is paginated by default, or that it only returns basic info).

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 extremely concise with two sentences, front-loading the core purpose and immediately stating the key limitation (no recursion). Every sentence provides unique information with no redundancy. It is well-structured and scannable.

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?

For a simple read-only list tool, the description is largely complete given that annotations cover safety. It states what it returns and that it does not recurse. It does not mention pagination (limit/offset) or response_format, but these are available in the schema. The only minor gap is unclear behavior when the directory does not exist or is empty, but that is not critical for tool selection. Overall, it provides enough context for an agent to call it correctly with minimal assumptions.

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 75%, meaning most parameters (limit, offset, directory) have descriptions in the schema. However, response_format is an enum without an explicit description, and the tool description does not mention it at all. The description does not add any new meaning to parameters beyond the schema, and it fails to clarify the response_format enum values (json vs markdown). With moderate coverage and no added value from the description, this is below the baseline of 3.

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 action ('List all files in a directory') and the resource (directory), with a specific scope ('Does not recurse into subdirectories'). This differentiates it from siblings like file_organizer_scan_directory which might perform deeper scans, and mentions the output (file names and paths). The verb and resource are specific and 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 does not provide guidance on when to use this tool versus alternatives. It does not mention any exclusions or conditions for choosing this tool over file_organizer_scan_directory or file_organizer_find_largest_files. An agent would have to infer usage from the tool name and description alone, which is insufficient.

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