Skip to main content
Glama

get_collision_info

Read-onlyIdempotent

Inspect a placed primitive component's collision setup and physics state—channel responses, event flags, simulate physics, mobility, and physics material—to diagnose why it fails to block or overlap.

Instructions

Read ONE placed primitive component's collision setup and physics state: collision enabled mode, per-channel responses (WorldStatic / WorldDynamic / Pawn / PhysicsBody), overlap and hit event flags, simulate-physics, mobility, and the physical material with its friction / restitution / density. The tool to answer "why does this not block / not overlap" without writing Python. Two limits from the code: it searches by component NAME across the world's actors but only inspects each actor's FIRST primitive component, so a secondary component (a second collider, a trigger next to a mesh) reports "not found" even though it exists; and it reads the component's live responses, NOT the profile definition -- for the profile itself use get_collision_profile (which is blind to +EditProfiles overrides), and prove a channel really blocks with raycast_scene.

Returns: { component_name: string, collision_info_found: bool, collision_info_message: string, collision_enabled: string, collision_type: string, collision_response: string, collision_enabled_state: string, collision_generate_overlap_events: bool, collision_generate_hit_events: bool, collision_simulate_physics: bool, collision_mobility: string, collision_response_world_static: string, collision_response_world_dynamic: string, collision_response_pawn: string, collision_response_physics_body: string, physics_material_is_default: bool, physics_material_name: string, physics_material_path: string, physics_material_surface_type: string, physics_material_friction: float, physics_material_restitution: float, physics_material_density: float, physics_material_raise_mass_to_power: float, physics_material_linear_damping: float (body), physics_material_angular_damping: float (body), physics_material_mass_scale: float (body) }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
component_nameYesName of the primitive component to query (must be its actor's first primitive component to be findable).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description goes further by disclosing two real code limits: it searches by component name but only inspects each actor's FIRST primitive component (so secondary colliders report 'not found'), and it reads live responses rather than the profile definition, which is blind to +EditProfiles overrides. These caveats materially affect interpretation of results.

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?

Purpose and use case are front-loaded, then limitations, then alternatives. It is dense and long, but with no output schema the return-field enumeration earns its space. Slightly over-stuffed in the return list, keeping it just below a 5.

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?

No output schema exists, so the description correctly carries the full return contract (component_name, collision_info_found, per-channel responses, physical material fields, etc.), and it discloses the search constraints an agent needs to interpret a 'not found' result. Nothing essential 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% and the schema already states the first-primitive-component constraint. The description reinforces it with concrete failure examples (a second collider, a trigger next to a mesh), which adds interpretive value beyond the schema's terse note, though it does not add new syntax.

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 ('Read ONE placed primitive component's collision setup and physics state') and enumerates exactly what is returned (collision mode, per-channel responses, event flags, physics, mobility, physical material). It explicitly distinguishes itself from get_collision_profile and raycast_scene, so an agent can route correctly without opening a 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?

Gives an explicit use case ('The tool to answer "why does this not block / not overlap" without writing Python') plus named alternatives with the condition that selects each: get_collision_profile for the profile itself, raycast_scene to prove a channel really blocks. This is textbook when/when-not guidance.

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