list_files

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

With no annotations, the description carries full burden. It does not disclose behavioral traits such as read-only nature, error handling, path resolution, or whether the tool may be expensive (e.g., large directories). The bare statement of functionality is inadequate.

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 concise (single phrase) and front-loaded, with no wasted text. However, it is perhaps too minimal for a tool with 4 parameters; a slightly longer description could improve completeness without harming conciseness.

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?

The tool has 4 parameters and no output schema; the one-line description does not explain the output format, the relationship between 'depth' and 'recursive', or the behavior when parameters conflict. More detail is needed for a complete understanding.

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 100% with Chinese descriptions for each parameter. The tool description adds no further parameter semantics, so the agent must rely solely on the schema. Baseline 3 is appropriate as schema suffices.

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 "列出目录内容或递归获取目录树" (List directory contents or recursively get directory tree) clearly states the action (listing) and the resource (directory), differentiating it from siblings like file_read (content) and file_search (search). It is specific and non-tautological.

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 no guidance on when to use this tool versus alternatives (e.g., file_search for searching, file_read for content). An agent must infer usage from context 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.