Skip to main content
Glama

set_mid_vector_param

DestructiveIdempotent

Override a vector (color) parameter on a transient Material Instance Dynamic by MID path and parameter name; changes apply at once and are not saved.

Instructions

Set a vector (color) parameter override on a transient Material Instance Dynamic (MID), found by object path or name as create_material_instance_dynamic or create_dynamic_material_on_actor return it; it takes effect at once and is never saved. param_name must be a global vector parameter of the MID's material (as get_mid_all_params lists it); any other name is refused and nothing is written. set is the read-back of the new color. Scalars and textures: set_mid_scalar_param, set_mid_texture_param.

Returns: { mid_object_path, param_name, old_value: {r, g, b, a}, new_value: {r, g, b, a}, set }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bNoNot read at the top level: the blue component goes in value
gNoNot read at the top level: the green component goes in value
rNoNot read at the top level: the red component goes in value
valueYesColor object {r, g, b, a}; a missing component is 0, a missing a is 1
param_nameYesName of a vector parameter of the MID's material
mid_object_pathYesObject path of the MID (from create_material_instance_dynamic)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv1.2.2
    • changedInput schema / properties / b / description
      Previous value: -"Blue component (0-1)"New value: +"Not read at the top level: the blue component goes in value"
    • changedInput schema / properties / g / description
      Previous value: -"Green component (0-1)"New value: +"Not read at the top level: the green component goes in value"
    • changedInput schema / properties / mid_object_path / description
      Previous value: -"Object path of the MID"New value: +"Object path of the MID (from create_material_instance_dynamic)"
    • changedInput schema / properties / param_name / description
      Previous value: -"Name of the vector parameter"New value: +"Name of a vector parameter of the MID's material"
    • changedInput schema / properties / r / description
      Previous value: -"Red component (0-1)"New value: +"Not read at the top level: the red component goes in value"
    • changedInput schema / properties / value / description
      Previous value: -"Color object {r, g, b, a} components (a defaults to 1)"New value: +"Color object {r, g, b, a}; a missing component is 0, a missing a is 1"
  2. First observedv1.1.0

TDQS

A4.5/5.0
Behavior4/5

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

With annotations already declaring readOnly=false, destructive=true and idempotent=true, the description still adds real behavioral context: the override is transient and never saved, it applies immediately, invalid param names are rejected with no write, and it returns old/new values plus a 'set' read-back. It does not clarify what happens to pre-existing overrides or whether a runtime/PIE context is required, so it stops short of 5.

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-loaded with the operation and scope, and the routing sentence and Returns line are compact and informative. The first sentence is long and semicolon-heavy, packing MID lookup, timing, persistence and validation into one clause chain, which slightly hurts scannability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, but the description compensates with an explicit Returns shape (mid_object_path, param_name, old/new color, set), and it documents the handle source, parameter validity and sibling alternatives. Remaining gaps are minor: the ignored top-level r/g/b parameters and any runtime/PIE precondition are left to the schema or unaddressed.

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 description coverage is 100%, so the schema would earn a baseline 3 on its own. The description adds meaning beyond it by constraining param_name to a global vector parameter enumerable via get_mid_all_params and by identifying where mid_object_path comes from; it says nothing extra about the top-level r/g/b alias parameters, which only the schema explains.

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 (set a vector/color parameter override on a transient MID) and pins the scope with 'takes effect at once and is never saved'. It explicitly routes the sibling variants by naming set_mid_scalar_param and set_mid_texture_param, so an agent can distinguish it from adjacent material-parameter tools 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?

Gives the prerequisite for the MID handle (object path from create_material_instance_dynamic or create_dynamic_material_on_actor), the validity requirement for param_name (must be a global vector param as get_mid_all_params lists it) and the failure mode ('any other name is refused and nothing is written'). It also names the alternatives for other parameter types, so the when-to-use decision is fully specified.

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