Skip to main content
Glama

instance

Create, delete, move, clone, or rename Roblox Studio objects with optional nested children and tags; operations are undoable.

Instructions

Create (with optional recursive children tree & tags), delete, move (reparent), clone or rename instances. Undoable. For scripts prefer script_write or file sync.

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": {
      "op": "<op>"
    },
    "name": "instance"
  }
}

Input Schema

NameRequiredDescriptionDefault
opYes
nameNocreate/clone/rename: new name.
pathNoTarget instance (delete/move/clone/rename).
tagsNoCollectionService tags to add on create/clone.
classNocreate: ClassName, e.g. Part, Folder, RemoteEvent, ScreenGui.
propsNocreate/clone: properties to set (same value format as set_props).
parentNocreate: parent path. move/clone: new parent.
studioNoOptional. Target Studio (name substring, place id or id). Only needed when several Studios are open and none was selected.
childrenNocreate: optional nested child specs { class, name?, props?, attributes?, tags?, children? } built in one atomic call.
attributesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.7/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full burden. It does add real behavioral context: operations are undoable, and create can build a whole nested subtree atomically. It omits the consequences for destructive paths—whether delete removes descendants, what happens on move/clone to a missing parent, and what is returned after each op—which matters for a five-op mutation tool.

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 tight sentences, front-loaded with the operation list, followed by the undoability note and the sibling routing hint. No filler and nothing buried.

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

Completeness3/5

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

For a 10-parameter, nested-object mutation tool with no annotations and no output schema, the description covers operations and one behavioral trait but leaves the agent guessing about destructive semantics, return values, and failure behavior. It is adequate to select the tool, less adequate to call it confidently in edge cases.

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 80%, so the schema already explains name, path, tags, class, props, parent, studio, and children. The description reinforces which params apply to create (children tree, tags) but adds no format or constraint details beyond what the schema states. Baseline 3 is appropriate.

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 names the specific resource (instances) and enumerates the exact operation set from the op enum: create, delete, move/reparent, clone, rename. It also clarifies scope for the create case (recursive children tree & tags). It falls short of 5 only because the concept of an 'instance' is never grounded (the schema's class examples carry that weight) and the multi-verb bundling makes it slightly harder to match against a single intent.

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?

It gives one explicit routing rule: 'For scripts prefer script_write or file sync,' which steers the agent away from this tool for script content. It also flags 'Undoable,' implying experimentation is safe. It stops short of explicit when-not guidance for structural mutations, e.g. when to use set_props instead of passing props here, or when tree is the better read counterpart.

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