Skip to main content
Glama

Create Directory

make_directory
Idempotent

Create a directory and any missing parent folders inside an allowed sandbox path, so nested project structures can be built safely in one step.

Instructions

Create a directory and any missing parents inside an allowed directory.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "path": "<path>"
    },
    "name": "make_directory"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesDirectory path

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=true, and openWorldHint=false, so the safety profile is covered. The description still adds real value beyond that by disclosing recursive parent creation and a sandbox boundary ('allowed directory'). It does not say what happens if the target already exists or how path violations are rejected, but the idempotent annotation covers the first case.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One sentence, front-loaded with the verb and resource, then the recursive and sandbox qualifiers. Nothing is wasted and nothing important is buried.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter creation tool with no output schema and full annotation coverage, the description supplies the two facts an agent actually needs: parents are created recursively and the target must be within the allowed root. Only minor gaps remain, such as explicit behavior on an existing target or on a disallowed path.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% for the single 'path' parameter, so the baseline applies. The description contributes one piece of meaning the schema lacks: the path must resolve inside an allowed directory, which constrains valid values. It does not clarify absolute vs relative path form, though that follows from the sandbox statement.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('Create a directory') and adds the recursive 'any missing parents' scope, which distinguishes it from a plain single-level mkdir. It does not explicitly name or contrast with siblings like list_directory, but the verb makes the intent unambiguous without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the verb and by the constraint 'inside an allowed directory', which tells the agent it must target the permitted root. There is no explicit when-to-use/when-not guidance and no statement about alternatives such as a plain file-write tool that might create parents implicitly.

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