创建目录

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

Annotations already cover the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), lowering the bar. The description does add one genuinely useful behavioral fact beyond them: read-only servers reject the call before connecting. It says nothing about what happens when the directory already exists or about permission errors beyond that.

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?

A single short sentence, front-loaded with the verb and resource, followed by the one caveat that matters. No filler or redundancy.

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 and both parameters are fully documented, so return values need not be explained. Purpose and one failure mode are covered; the only gap is guidance on choosing this tool over sibling directory-creating operations.

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% for both parameters (path and optional server alias), so the schema already carries the semantics. The description adds no path syntax, default-server, or aliasing detail beyond it, making the baseline 3 appropriate.

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+resource (创建目录) scoped to the virtual remote path, which is concrete enough for an agent to act on. It does not, however, distinguish itself from siblings that also materialize directories (e.g. upload_dir), leaving the routing decision implicit.

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?

There is no when-to-use guidance and no named alternative among the 13 siblings. The clause about read-only servers is a precondition caveat, not usage direction, so the agent gets no help choosing this over upload_dir or list_dir.

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