Skip to main content
Glama

move_nodes

Reparent or reorder nodes in a Godot scene while keeping each subtree intact, then save once at the end. Rejects root, instanced, inherited, or invalid targets.

Instructions

Move nodes to another parent and/or child position in a scene, each subtree kept whole (owners, groups, connections). Always-array moves, applied in order. Saves once at the end. Returns: results[] per move with success, newNodePath and index read back, or error; warnings leads when a NodePath value no longer leads where it did. Refused per entry: the root, a node inside an instance or inherited, a target inside the node, a name taken at the target. Errors while a runtime session is live.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "projectPath": "<projectPath>",
      "scenePath": "<scenePath>",
      "moves": "<moves>"
    },
    "name": "move_nodes"
  }
}

Input Schema

NameRequiredDescriptionDefault
movesYesMoves to apply in order. Each names a node and gives newParentPath, index or both.
scenePathYesScene file path relative to the project
projectPathYesPath to the Godot project directory

Output Schema

NameRequiredDescriptionDefault
resultsYes
warningsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv4.0.1

TDQS

A3.9/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so well: it discloses mutation semantics (single save at the end), ordering semantics (applied in order), structural invariants (owners, groups, connections kept whole), enumerated per-entry refusals (root, instanced/inherited nodes, self-nesting targets, name collisions), and a precondition (errors while a runtime session is live).

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 purpose, then batch behavior, then return shape, then refusal rules; nearly every clause carries information. Minor deductions for the garbled phrasing 'warnings leads when a NodePath value no longer leads where it did' and for restating the return shape despite an output schema existing.

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?

Complete enough for a batch mutation tool: preconditions, ordering, atomicity of the save, per-move failure reporting and refusal cases are all covered. The only redundancy is describing the results[] shape when an output schema is supplied, and partial-failure semantics across moves could be stated more sharply.

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

Parameters3/5

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

Schema description coverage is 100%, including rich per-field docs for nodePath, newParentPath and index, so the schema already does the heavy lifting. The description adds only the array-level ordering note ('Always-array moves, applied in order'), which is a modest increment over structured data.

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?

States a specific verb and resource ('Move nodes') plus a precise scope: reparenting and/or reordering within a scene, with subtrees preserved. This clearly distinguishes it from add_node, duplicate_node and delete_nodes, though it never names a sibling or an alternative route to the same outcome.

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?

Usage context is implied rather than prescribed: 'Always-array moves, applied in order' and 'Saves once at the end' tell the agent how a call behaves, and the refusal list effectively says where the tool will not work. There is no explicit when-to-use-this-vs-another-tool guidance, so the agent must infer that reordering/reparenting is this tool's job.

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