godot-omni

Overview Schema Source Related Servers Discussions Admin

compute_manage

Manage GPU compute pipelines in Godot: create GLSL compute shaders, inspect RenderingDevice capabilities, and dispatch compute workloads to read back output data.

Instructions

GPU Compute Shaders, RenderingDevice Uniform Buffers, and GPU Pipeline Execution.

Ops:

create_shader(shader_path="res://shaders/compute_example.glsl", code="") Create a GLSL compute shader template file.
get_device_info() Inspect RenderingDevice capabilities, workgroup limits, and driver version.
run_compute(shader_path, input_buffer=[...], x_groups=1, y_groups=1, z_groups=1) Compile and dispatch a compute pipeline on the GPU and read back output data.

Canonical call shape: {"op": "<verb>", "params": {...}}. Flat op parameters are accepted as a compatibility alias when the client transmits them; op and session_id remain top-level.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`op`	Yes
`params`	No
`session_id`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Addedv5.0.28Sep 23, 2026

TDQS

A3.9/5.0

Behavior4/5

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

No annotations are provided, so the description carries the full burden of disclosure. It does disclose per-operation behavior: creating a shader template file, inspecting device capabilities, and compiling/dispatching a compute pipeline with read-back. It does not discuss failure modes, overwrite behavior, or resource cleanup, but the core effects of each op are clear.

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?

The description is front-loaded with the domain, then a compact bullet list of operations, followed by a single necessary call-shape note. Every line earns its place, with no filler or tautology.

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?

For a dispatcher-style tool with three operations and no annotations, the description covers invocation shape, operation names, and per-op behavior; an output schema exists so return-value details need not be repeated. It still omits prerequisites and precise input_buffer semantics, but is reasonably complete for selecting and invoking the tool.

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 0%, and the description compensates by providing op-specific parameter names, defaults, and brief purpose (e.g., shader_path, code, input_buffer, x/y/z_groups). It leaves exact buffer element types and input_buffer format implicit, but adds meaning that the generic params object cannot.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies a specific domain ('GPU Compute Shaders, RenderingDevice Uniform Buffers, and GPU Pipeline Execution') and lists three operations with clear verbs: create_shader, get_device_info, and run_compute. It does not explicitly differentiate from sibling tools like shader_manage or rendering_manage, but the resource scope is unmistakable.

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?

The header and operation list imply this tool is for GPU compute and RenderingDevice workflows, and the canonical call shape explains how to invoke it. However, there is no explicit 'use this instead of X' guidance or exclusions relative to the many shader/rendering sibling tools, so routing is left mostly to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server