create_directoryCreates a directory and any missing parent folders; an existing folder is not an error. Writing is refused where folder policy forbids it.
Create a directory (and parents); an existing one is not an error. Refused where the zone policy forbids writing.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly=false, idempotent=true, destructive=false, so the safety profile is covered. The description still adds real value beyond them: it confirms parent creation (mkdir -p semantics), restates idempotency as 'existing one is not an error', and discloses a policy-based permission failure mode not captured in the annotations.
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 short clauses, front-loaded with the core action and behavior, with zero filler. Every clause carries distinct information (recursive creation, idempotency, authorization failure).
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 one-param mutation with no output schema and rich annotations, the description covers behavior, idempotency, and failure modes well. The only meaningful omission is what form 'path' must take and where writing is permitted.
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?
The single 'path' parameter has zero description coverage in the schema, and the description supplies no semantics either — no indication of relative vs absolute paths, allowed roots, or format. With one undocumented param and 0% coverage, the description fails to compensate for the gap.
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 clear verb+resource ('Create a directory') and immediately extends it with recursive behavior ('and parents'). No sibling in the list performs directory creation, so the tool is functionally distinguishable, but the description never routes the agent relative to any sibling, keeping it a notch below a 5.
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?
Usage is only implied: the agent learns an existing directory is not an error and that zone policy can refuse the write, but there is no explicit when-to-use, when-not-to-use, or alternative named. It is adequate context without routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.