Skip to main content
Glama

create_instance

Create a single Roblox instance under a parent path in the edit copy, set its properties before parenting, and return its path as one undoable Studio step.

Instructions

Create one new instance in the edit copy and return its path. Recorded as one Studio undo step. A property that fails to set is skipped without an error, so read it back with get_properties when it matters. For several instances use create_tree (a nested hierarchy) or batch (mixed operations), which run in one call.

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": {
      "className": "<className>",
      "parentPath": "<parentPath>"
    },
    "name": "create_instance"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoName for the new instance. Defaults to the class name.
placeNoTarget place (PlaceId or project name). Defaults to the bound/sole connected place.
classNameYesRoblox class to create, e.g. "Part", "Frame", "ModuleScript". Must be creatable with Instance.new.
parentPathYesParent to create the instance under. Dot path from the DataModel root, e.g. "Workspace.Map.Door" or "StarterGui.HUD.Frame". A leading "game." is optional; a duplicate sibling name takes the suffix Tufan prints, e.g. "Part (2)".
propertiesNoProperty name to value, applied before parenting. Write a primitive (string, number, boolean) or a typed wrapper: {Vector3:[x,y,z]}, {Color3:[r,g,b]} (0-1), {UDim2:[xScale,xOffset,yScale,yOffset]}, {CFrame:[x,y,z] or all 12 components}, {EnumItem:"Enum.Material.Wood"}, {BrickColor:"Bright red"}.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.1.1
    • addedInput schema / properties / className / description
      Added value: +"Roblox class to create, e.g. \"Part\", \"Frame\", \"ModuleScript\". Must be creatable with Instance.new."
    • addedInput schema / properties / name / description
      Added value: +"Name for the new instance. Defaults to the class name."
    • addedInput schema / properties / parentPath / description
      Added value: +"Parent to create the instance under. Dot path from the DataModel root, e.g. \"Workspace.Map.Door\" or \"StarterGui.HUD.Frame\". A leading \"game.\" is optional; a duplicate sibling name takes the suffix Tufan prints, e.g. \"Part (2)\"."
    • changedInput schema / properties / properties / description
      Previous value: -"name -> value (primitive or {Vector3:[x,y,z]} etc.)"New value: +"Property name to value, applied before parenting. Write a primitive (string, number, boolean) or a typed wrapper: {Vector3:[x,y,z]}, {Color3:[r,g,b]} (0-1), {UDim2:[xScale,xOffset,yScale,yOffset]}, {CFrame:[x,y,z] or all 12 components}, {EnumItem:\"Enum.Material.Wood\"}, {BrickColor:\"Bright red\"}."
  2. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the annotations, it discloses two non-obvious behaviors: the operation is recorded as exactly one Studio undo step, and property assignments that fail are silently skipped rather than raising an error. The silent-failure warning is exactly the kind of trap an agent needs pre-warned, and nothing conflicts with readOnlyHint=false / destructiveHint=false.

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?

Three sentences, zero filler: capability first, then the silent-skip caveat, then the sibling routing. Each sentence changes how an agent would call the tool.

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

Completeness5/5

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

For a 5-parameter mutation tool with no output schema, the description covers return value (its path), the undo granularity, failure semantics, and the scaling alternatives. Nothing needed to invoke it correctly is absent.

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%, with className, parentPath dot-path syntax, place resolution, and typed property wrappers all documented in the schema itself. The description adds no parameter-specific detail beyond the read-back advice, so the baseline 3 applies.

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

Purpose5/5

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

"Create one new instance in the edit copy and return its path" gives a specific verb, resource, cardinality (one), and target (edit copy), which immediately separates it from create_tree and batch.

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

Usage Guidelines5/5

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

Explicitly routes multi-instance work to create_tree (nested hierarchy) or batch (mixed operations) in a single call, and tells the agent to verify with get_properties when property values matter. When-to-use and when-to-use-something-else are both stated.

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