Skip to main content
Glama

add_impulse_to_actor

Kick an actor's physics body by applying an impulse or mass-independent velocity change to its primitive component, optionally at a world location or named bone in Unreal Engine.

Instructions

Kick a physics body: apply an impulse (or, with vel_change, a mass-independent velocity change) to an actor's primitive component, optionally at a world location for torque via AddImpulseAtLocation, or on a named skeletal bone. Acts on the EDITOR world, where nothing is simulating unless the component has simulate_physics on -- so on a resting editor actor this is a no-op that still reports applied:true; verify with a transform re-read, and for gameplay-time forces drive it in PIE.

Returns: { actor_name: string, component_name: string, applied: bool }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
impulseNo[x, y, z] impulse vector in world units (required)
locationNoOptional [x, y, z] world location for AddImpulseAtLocation (omit to use AddImpulse)
bone_nameNoOptional skeletal bone name to apply the impulse to
actor_nameYesDisplay label or internal name of the target editor-world actor (required)
vel_changeNoOptional; if true, impulse is treated as a velocity change (mass-independent)
component_nameNoOptional primitive component name (defaults to the actor's RootComponent)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A4.6/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false and destructiveHint=false, and the description goes well beyond them by disclosing the editor-world no-op trap and that applied:true can be reported even when nothing moved. That is exactly the silent-failure detail annotations cannot express; minor deduction for not restating mutation side effects like whether state changes persist.

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-loads the core purpose before the editor-world caveat, and every clause carries information. The second sentence is long and dense with multiple subordinate clauses, slightly reducing scannability, but no sentence is filler.

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 6-parameter physics tool with no output schema, the description supplies the return shape (actor_name, component_name, applied) and the crucial caveat that applied can be misleading. 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 semantic intent beyond the schema: vel_change is a mass-independent velocity change, and providing location introduces torque via AddImpulseAtLocation. These clarify why a caller would pick each parameter variant, though exact units/axes still come from the schema.

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?

Names a specific verb and resource (apply an impulse to an actor's primitive component) and immediately frames the two modes (direct impulse vs vel_change) plus the location/bone variants. An agent can distinguish this from transform setters or physics-property tools without opening the schema.

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 states the when-not condition: on the editor world it is a no-op unless simulate_physics is on, and directs the agent to drive gameplay-time forces in PIE instead. It also advises verifying with a transform re-read, giving concrete operational guidance rather than just context.

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