Skip to main content
Glama
CarlxsMG

UEAgent

by CarlxsMG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

set_material_node_param

DestructiveIdempotent

Sets one property on a UMaterial expression node by node_id, refuses values that do not parse, marks the material dirty, and returns the read-back value.

Instructions

Write one property of an expression node of a UMaterial asset (not an instance), found by its object name node_id. param_name names the property on every node type (R on Constant, DefaultValue or SliderMax on ScalarParameter, Constant on Constant3Vector and Constant4Vector, DefaultValue on VectorParameter...); ParameterName renames a node that has a parameter name. A value that does not parse for the property is refused and nothing is written. No undo, no save: it runs PostEditChange and marks the material dirty (persist with save_asset). value_after is the property read back. Instances: set_material_instance_param.

Returns: { material: string, node_id: string, param_name: string, value: string, value_after: string }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
valueNoText to write: a number for a numeric property, "(R=1,G=0.5,B=0,A=1)", "[1,0.5,0,1]" or "1,0.5,0" for a linear color, the new name for ParameterName, else UE import text for the property; omitted means empty text.
node_idYesId of the target expression in the material
param_nameYesName of the property to set (e.g. "ParameterName", "R", "DefaultValue")
material_pathYesMaterial asset path

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.2.2
    • changedInput schema / properties / value / description
      Previous value: -"Text to write: a number for Constant and ScalarParameter, \"(R=1,G=0.5,B=0,A=1)\" for the vector nodes (unparsable text gives black), the new name for ParameterName, else UE import text for the property; omitted means empty text."New value: +"Text to write: a number for a numeric property, \"(R=1,G=0.5,B=0,A=1)\", \"[1,0.5,0,1]\" or \"1,0.5,0\" for a linear color, the new name for ParameterName, else UE import text for the property; omitted means empty text."
  2. Changed1 schema field changedv1.2.0
    • changedInput schema / properties / value / description
      Previous value: -"String value to import (parsed per property type)"New value: +"Text to write: a number for Constant and ScalarParameter, \"(R=1,G=0.5,B=0,A=1)\" for the vector nodes (unparsable text gives black), the new name for ParameterName, else UE import text for the property; omitted means empty text."
  3. First observedv1.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the annotations: it discloses that unparseable values are refused with nothing written, that there is no undo and no save, that PostEditChange fires and the material is marked dirty, and that value_after is the read-back. This is exactly the kind of mutation/durability context the annotations (destructiveHint, idempotentHint) cannot convey.

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?

Dense but front-loaded with the core purpose and scope before the node-type mapping and save/dirty behavior. Every sentence carries information; it is slightly information-heavy but not padded.

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?

Complete for a mutation tool: purpose, alternative routing, refusal/failure behavior, persistence obligations and even the return shape are all present, compensating for the absence of an output schema.

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 coverage the baseline is 3, but the description adds real meaning: it maps param_name to node types (R on Constant, DefaultValue/SliderMax on ScalarParameter, Constant on Constant3Vector/Constant4Vector, DefaultValue on VectorParameter) and explains the ParameterName rename case. This is semantic guidance the schema's short example list does not provide.

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 ('Write one property') and resource ('an expression node of a UMaterial asset'), immediately scoping it as not-an-instance. It names the sibling it is not (set_material_instance_param), so an agent can distinguish it without opening other schemas.

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?

Explicitly routes instance edits to set_material_instance_param and notes the post-write step (persist with save_asset). It implies when to use it (writing a single expression-node property) but does not spell out broader when-not conditions beyond the instance case.

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