Skip to main content
Glama

set_blueprint_component_collision

DestructiveIdempotent

Sets collision on a Blueprint component template by applying profile, collision_enabled, then per-channel responses in order. Use for collision edits, not generic property changes.

Instructions

Set collision on a Blueprint component TEMPLATE (own SCS or inherited via ICH), not on a spawned actor, applying in this order: profile through SetCollisionProfileName (which expands the profile into the FBodyInstance response array -- a raw reflection write would set the string and leave BodyInstance inconsistent, and that is the whole reason this is a separate tool), then collision_enabled, then per-channel responses. Use it instead of set_blueprint_component_property for anything collision-shaped. Unknown channel, response or collision_enabled names are hard errors, never a silent default. Note the ORDER: a later profile would reset the per-channel responses, so responses always win here.

Returns: { success, data: { blueprint_name, component_name, source ("scs" | "inherited-ich" | "inherited-native": which template was written), profile?, collision_enabled?, responses_applied: [{channel, response}], compiled } } -- responses_applied lists ONLY the per-channel writes; profile and collision_enabled appear as their own fields only when they were given. Nothing is re-read: verify with get_blueprint_component_property or get_collision_info.

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.
compileNoOptional bool (default FALSE): compile the Blueprint afterwards so the FBodyInstance change reinstances on the next spawn/PIE. Without it the edit stays in the uncompiled template.
profileNoCollision profile name, e.g. "BlockAll" (optional). Applied FIRST, so it does not undo the per-channel responses below.
responsesNoObject mapping channel -> response, e.g. {"Visibility":"Ignore","ECC_Pawn":"Overlap"} (optional). Channels accept the friendly display name or an ECC_* token (custom project channels included); responses are Ignore, Overlap or Block. An unknown channel is refused rather than defaulting to WorldStatic.
blueprint_nameNoBlueprint asset path or name (required)
blueprint_pathNoAlias of `blueprint_name` (same value, same meaning). Accepted because sibling tools spell this parameter differently; prefer `blueprint_name`.
component_nameYesComponent to modify (required); must resolve to a UPrimitiveComponent or the call errors with "no collision to set"
return_messagesNoNo effect here: it is only read by the compile this tool may run internally, whose message log is discarded. Call compile_blueprint directly if you want the messages.
collision_enabledNoECollisionEnabled value name: NoCollision, QueryOnly, PhysicsOnly or QueryAndPhysics (optional). Any other string is an error.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A4.9/5.0
Behavior5/5

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

Annotations cover the safety profile (destructive=true, idempotent=true), and the description goes well beyond them: it explains why the tool exists (a raw reflection write leaves FBodyInstance inconsistent), that unknown channel/response/enabled names are hard errors rather than silent defaults, the ordering hazard, and that nothing is re-read so verification requires another tool. It also documents the PIE refusal consequence (editor-killing GC leak / silent no-write).

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?

Front-loads the single most important distinction (template vs spawned actor) before any detail. The dense returns block and ordering notes are load-bearing rather than filler, and with no output schema present the Returns section is necessary rather than redundant.

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 9-parameter destructive mutation with no output schema, the description covers the return shape, the ordering semantics, the hard-error behavior, and the PIE precondition. Nothing an agent needs to call it safely appears to be 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 meaning: the order in which profile/collision_enabled/responses are applied, that responses always win over a profile, and that per-channel names accept either friendly names or ECC_* tokens. It stops short of documenting every param (e.g. it defers `force`/`compile` detail to the schema), hence a 4 rather than 5.

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+resource ('Set collision on a Blueprint component TEMPLATE') and immediately scopes it against the alternative target ('not on a spawned actor'), naming SCS/ICH/native template sources. It also names the sibling it replaces, so an agent can distinguish it from set_blueprint_component_property and set_actor_component_collision without opening any 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 says 'Use it instead of set_blueprint_component_property for anything collision-shaped', giving both the condition and the alternative. It further specifies application order (profile, then collision_enabled, then responses) and warns that a later profile would reset responses, so the agent knows how the inputs interact.

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