2021 Roblox Studio MCP Bridge

Overview Schema Source Related Servers Discussions Admin

create_instance

Creates a new Instance in the Roblox DataModel by class name, allowing optional parent, name, and properties to build or modify game objects.

Instructions

Creates a new Instance in the DataModel

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>"
    },
    "name": "create_instance"
  }
}

Input Schema

Name	Required	Default
`name`	No
`parent`	No	game.Workspace
`className`	Yes
`properties`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv1.5.6Sep 30, 2026
- removedInput schema / properties / className / description
```
Removed value: -"Class name of the instance (e.g. 'Part', 'Folder', 'Script')"
```
- removedInput schema / properties / name / description
```
Removed value: -"Name for the new instance"
```
- removedInput schema / properties / parent / description
```
Removed value: -"Parent path (e.g. 'game.Workspace')"
```
- removedInput schema / properties / properties / description
```
Removed value: -"Key-value dictionary of initial properties"
```
First observedv1.0.0Sep 12, 2026

TDQS

D1.9/5.0

Behavior1/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It says only that the tool 'Creates' something, without stating permissions required, side effects, reversibility, or what happens to existing instances.

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

Conciseness2/5

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

The single sentence is front-loaded but far too terse for a four-parameter mutation tool, leaving critical information absent. This is under-specification rather than effective conciseness.

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

Completeness1/5

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

Given a mutation tool with no annotations, no output schema, and four undocumented parameters including a nested object, the description is completely inadequate. An agent cannot safely call this tool without opening and inferring from the schema alone.

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

Parameters1/5

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

Schema description coverage is 0% across four parameters, including a nested 'properties' object, and the description adds no meaning for any of them. It does not explain className, parent defaults, name, or the properties structure.

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 ('Creates') and resource ('Instance in the DataModel'), so the basic action is clear. However, it does not distinguish this tool from siblings like delete_instance or inspect_instance, nor does it clarify scope beyond the generic 'DataModel'.

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

Usage Guidelines1/5

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

Provides no guidance on when to use this tool versus alternatives such as execute_luau or multi_edit, and no prerequisites or exclusions are mentioned. An agent must infer usage entirely from the name.

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