Skip to main content
Glama

add_rig_bone

Add a bone to a Control Rig Blueprint hierarchy under a parent or at the root, then compile and save. Refuses if PIE is running unless forced.

Instructions

Add a bone to the hierarchy of a Control Rig Blueprint, under parent_name or at the root, then compile and save the blueprint. The engine keeps names unique, so element_key is the name the bone really got. Refused while PIE runs unless force is set.

Returns: { asset_path: string, element_key: string, element_type: string, parent: string, bone_count: int, null_count: int, control_count: int, curve_count: int, other_count: int, total: int, saved: bool, save_error: string }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
forceNoOptional. This command is REFUSED while a Play-in-Editor session is running: it either compiles a Blueprint (the reinstancer can retain a world, and CheckForWorldGCLeaks is Fatal -- it KILLS the editor) or writes to disk (Editor.AllowSavingAssetsDuringPIE=0 makes the engine refuse the write, so it would report success without writing a byte). Stop PIE and retry instead; force=true runs it anyway, at your own risk.
scaleNoOptional [x, y, z] scale for the new bone.
locationNoOptional [x, y, z] world location for the new bone.
rotationNoPREFERRED: the OBJECT {"roll":R,"pitch":P,"yaw":Y} (any subset, absent axes are 0). The ARRAY form below is [pitch, yaw, roll] -- its index 2 is ROLL, NOT yaw, which once put a PlayerStart on its side. Optional [pitch, yaw, roll] world rotation for the new bone.
bone_nameYesName of the new bone
parent_nameNoExisting BONE to parent the new bone under; omitted or empty puts it at the root
control_rig_pathYesControl Rig Blueprint asset path, e.g. "/Game/Rigs/CR_Hero"

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.2.0
    • changedInput schema / properties / control_rig_path / description
      Previous value: -"Path to the UControlRigBlueprint asset"New value: +"Control Rig Blueprint asset path, e.g. \"/Game/Rigs/CR_Hero\""
    • changedInput schema / properties / parent_name / description
      Previous value: -"Optional existing bone name to parent the new bone under."New value: +"Existing BONE to parent the new bone under; omitted or empty puts it at the root"
  2. First observedv1.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations declare the write/non-destructive/non-idempotent profile, and the description adds substantial context beyond that: it compiles and saves the blueprint, the engine enforces unique names so element_key is the actual assigned name, and it explains the PIE refusal risk (compile can kill the editor, save can silently no-op). This is exactly the behavioral detail annotations cannot carry.

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

Conciseness4/5

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

Front-loaded with purpose and placement, then the PIE caveat, then the return shape. The long Returns enumeration is justified because no output schema exists. Slightly dense, but every sentence carries information.

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 7-parameter mutating tool with no output schema, the description covers the side effects (compile + save), the failure mode (PIE), the naming outcome, and the full return payload. Nothing an agent needs to call it correctly is missing.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds real semantics beyond the schema: parent_name omission/empty means root placement, force overrides the PIE refusal, and element_key reflects the engine-assigned name rather than the requested one. That clarifies the request-vs-result relationship the schema cannot express.

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?

States a specific verb and resource ('Add a bone to the hierarchy of a Control Rig Blueprint') plus the two placement modes (under parent_name or at root). This clearly separates it from siblings like add_bone, add_virtual_bone, add_rig_control, and add_rig_null, which operate on different asset types or element kinds.

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?

Gives concrete usage context: parent under an existing bone or root, and the critical condition that the operation is refused while PIE runs unless force is set. It stops short of naming sibling alternatives (e.g., add_bone vs add_rig_bone), but the when-to-use and the PIE constraint are explicit.

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

Deploy Server

Other Tools