Skip to main content
Glama

create_directory

Creates a new directory in a WISP server filesystem when one is required; this changes filesystem state and needs WISP_ALLOW_FILE_WRITES enabled.

Instructions

Create a directory in the server filesystem. Use only when a new directory is required; this mutates filesystem state and requires WISP_ALLOW_FILE_WRITES.

Input Schema

NameRequiredDescriptionDefault
pathYesPath in the selected server filesystem, starting from its root.
server_idNoWisp server ID. Omit to use the configured WISP_SERVER_ID default.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.4.2
    • addedInput schema / properties / path / description
      Added value: +"Path in the selected server filesystem, starting from its root."
    • addedInput schema / properties / server_id / description
      Added value: +"Wisp server ID. Omit to use the configured WISP_SERVER_ID default."
  2. First observedv1.4.1

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the safety profile is partly known. The description adds meaningful context beyond them: this mutates filesystem state and requires the WISP_ALLOW_FILE_WRITES environment flag enabled. It does not say what happens on an existing path (relevant given idempotentHint=false) or whether parent directories are created, which is the main remaining gap.

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?

Two short sentences, front-loaded with the action and immediately followed by the usage constraint and prerequisite. No filler or redundancy.

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 simple two-parameter, single-purpose mutation with full schema coverage and annotations, the description covers purpose, gating condition, and the write-permission prerequisite. Only the edge-case behavior (existing directory, implicit parent creation) is left unexplained, which is a minor gap at this complexity level.

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 coverage is 100%, so both 'path' and 'server_id' are already documented with their semantics and default behavior. The description adds no path format, nesting, or server-selection guidance beyond the schema, so the baseline of 3 applies.

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?

States a specific verb and resource: 'Create a directory in the server filesystem.' An agent can distinguish it from list_directory, delete_file, and write_file by name and description. No explicit sibling routing, but the operation is unambiguous.

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

Usage Guidelines4/5

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

'Use only when a new directory is required' gives a clear negative-leaning condition, and the WISP_ALLOW_FILE_WRITES prerequisite is a real gating rule. It stops short of naming an alternative for directory creation (there is none among siblings) or saying what to do if the path already exists.

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