godot-omni

Overview Schema Source Related Servers Discussions Admin

batch_execute

Run a sequence of Godot editor sub-commands in one call, stopping at the first error and rolling back changes for atomic scene edits.

Instructions

Execute a list of editor sub-commands in order, stopping on first error.

Each item must be {"command": "<plugin_command>", "params": {...}}. Use the underlying plugin command names (e.g. create_node, set_property, delete_node, attach_script), not the MCP tool names. Commands run sequentially; execution stops at the first error. When undo is True (default), any successful sub-commands are rolled back via the scene's undo history if a later sub-command fails, producing atomic-on-failure semantics.

With preview=True, only create_node/delete_node commands are accepted; returns the scene node list before and after, then undoes all changes. To keep the proposed change, call again with preview=False.

Use this to compose multi-step edits (create node + set property + attach script) into a single tool call. Rollback works for sub-commands that modify the currently edited scene. batch_execute itself is not allowed as a sub-command.

Scene paths are relative to the edited scene root (e.g. "/Main/Enemy"), NOT runtime "/root/..." paths. The example below assumes the scene root is named "Main" — substitute the actual root name.

Input Schema

TableJSON Schema

Name	Required	Description
`undo`	No	Roll back succeeded sub-commands on failure. Default True.
`preview`	No
`commands`	Yes	List of `{"command": str, "params": dict}` items.
`session_id`	No	Optional Godot session to target. Empty = active session.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv5.0.36Sep 24, 2026
- addedInput schema / properties / preview
```
Added value: +{
+  "default": false,
+  "type": "boolean"
+}
```
First observedv4.1.0Sep 17, 2026

TDQS

A4.7/5.0

Behavior5/5

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

With no annotations provided, the description carries the full burden, and it does so thoroughly. It discloses sequential execution, first-error stopping, atomic rollback via undo history, preview-mode behavior with before/after node lists, the scope of rollback support, and scene-root-relative path conventions. This gives the agent accurate expectations about side effects and failure behavior.

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 description is long but information-dense and front-loaded with the core behavior. It loses a point because it repeats 'stops at the first error' after already stating it in the first sentence, and it references 'the example below' without actually providing an example in the visible text.

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 complex composite tool with no annotations, the description covers the command contract, execution semantics, failure rollback, preview path, path convention, and key constraints. The presence of an output schema relieves it from detailing return values, so nothing essential is missing for an agent to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although schema coverage is 75%, the description adds meaning well beyond the schema: it specifies the exact item shape (`{"command": ..., "params": ...}`), which plugin commands are expected, the semantics of preview=True and undo, and path conventions. This materially helps agents construct valid parameters.

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?

The description opens with a specific action: 'Execute a list of editor sub-commands in order, stopping on first error.' It clearly distinguishes itself from the sibling MCP tools by instructing agents to use underlying plugin command names, not MCP tool names, and frames its purpose as composing multi-step edits into one call.

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?

It explicitly states when to use the tool: 'Use this to compose multi-step edits (create node + set property + attach script) into a single tool call.' It also gives concrete constraints like batch_execute not being allowed as a sub-command and preview mode restrictions. It stops short of naming alternative individual tools, but the use case guidance is clear.

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

Deploy Server