Skip to main content
Glama
CarlxsMG

UEAgent

by CarlxsMG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

add_collision_profile

Destructive

Creates or replaces a project collision profile and writes Config/DefaultEngine.ini. Set object type, collision enabled, and channel responses; read back with get_collision_profile.

Instructions

Create a project collision profile, or replace an existing one of that name in full (omitted fields reset, custom responses cleared, can_modify not checked), then write Config/DefaultEngine.ini via TryUpdateDefaultConfigFile, unverified. Returns custom_response_count and already_existed; read it back with get_collision_profile.

Returns: { profile_name: string, object_type_name: string, collision_enabled: string, custom_response_count: int, already_existed: bool }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
can_modifyNoWhether this profile is user-editable in the editor UI. Defaults to true.
help_messageNoEditor tooltip text.
profile_nameYesName of the collision profile to create or replace, e.g. "MyPawnProfile"
custom_responsesNo[{channel: string, response: "Block"|"Ignore"|"Overlap"}, ...] per-channel overrides
object_type_nameYesChannel this profile's object type resolves to, e.g. "WorldDynamic" or a custom channel's friendly name
collision_enabledNo"NoCollision" | "QueryOnly" | "PhysicsOnly" | "QueryAndPhysics" | "ProbeOnly" | "QueryAndProbe". Defaults to "QueryAndPhysics".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.2.0
    • changedInput schema / properties / profile_name / description
      Previous value: -"Profile name"New value: +"Name of the collision profile to create or replace, e.g. \"MyPawnProfile\""
  2. First observedv1.1.0

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already flag destructive mutation, but the description adds substantial detail beyond them: omitted fields reset, custom responses cleared, can_modify not checked, and Config/DefaultEngine.ini is written via TryUpdateDefaultConfigFile without verification.

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?

The operation and dangerous replacement semantics are front-loaded, but the phrase 'Returns custom_response_count and already_existed' is immediately repeated by the full Returns object, a minor redundancy.

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 destructive mutation with no output schema, the description sufficiently covers full-replacement behavior, the config-file side effect, the unverified write, and the return shape.

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?

With 100% schema description coverage the baseline is 3, but the description adds important omission semantics for custom_responses and can_modify, which are not fully captured by the per-field schema descriptions.

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 ('Create a project collision profile, or replace an existing one of that name in full') and distinguishes the operation from the sibling read tool by pointing to get_collision_profile.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explains create-vs-replace behavior and tells the agent to read back with get_collision_profile, but does not say when to choose this tool over related tools like add_collision_channel or audit_collision_profiles, nor when not to use it.

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