Skip to main content
Glama

disconnect_signal

Destructive

Removes a signal connection between two nodes in a Godot scene and saves the change to the .tscn file. Use get_node_signals first to confirm the connection exists.

Instructions

Remove a signal connection between two nodes and persist the change in the .tscn. Use get_node_signals first to confirm the connection exists; connect_signal puts it back. Saves automatically. Returns: nodePath, signal, targetNodePath, method and connected, read back from the saved scene: false once the connection is gone, null with a leading warning if that read failed. Errors if the connection does not exist. Errors while a runtime session is live on this project.

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>",
      "nodePath": "<nodePath>",
      "signal": "<signal>",
      "targetNodePath": "<targetNodePath>",
      "method": "<method>"
    },
    "name": "disconnect_signal"
  }
}

Input Schema

NameRequiredDescriptionDefault
methodYesMethod name on the target node
signalYesSignal name on the source node
nodePathYesSource node path from scene root
scenePathYesScene file path relative to the project
projectPathYesPath to the Godot project directory
targetNodePathYesTarget node path from scene root

Output Schema

NameRequiredDescriptionDefault
methodYes
signalYes
nodePathYes
warningsNo
connectedYesWhether the saved scene holds the connection. Null when the scene could not be read back.
targetNodePathYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv4.0.1
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "connected": {
      +      "description": "Whether the saved scene holds the connection. Null when the scene could not be read back.",
      +      "type": [
      +        "boolean",
      +        "null"
      +      ]
      +    },
      +    "method": {
      +      "type": "string"
      +    },
      +    "nodePath": {
      +      "type": "string"
      +    },
      +    "signal": {
      +      "type": "string"
      +    },
      +    "targetNodePath": {
      +      "type": "string"
      +    },
      +    "warnings": {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    }
      +  },
      +  "required": [
      +    "nodePath",
      +    "signal",
      +    "targetNodePath",
      +    "method",
      +    "connected"
      +  ],
      +  "type": "object"
      +}
  2. Addedv3.1.1
  3. Removedv3.0.0
  4. Addedv1.0.0

TDQS

A4.4/5.0
Behavior4/5

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

Beyond destructiveHint=true, it discloses that the change is written to disk automatically, that the return values are read back from the saved scene, and that a failed read yields null with a warning. The two error modes (nonexistent connection, live runtime session) are spelled out. It stops short of saying whether the operation is reversible beyond re-calling connect_signal or whether the save can be rolled back.

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?

Purpose and disk-persistence effect are front-loaded, and each following sentence adds a precondition, an alternative, or an error mode. The "Returns:" sentence is dense and slightly run-on with its trailing clause, but no sentence is filler.

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 destructive, six-required-parameter mutation with annotations covering only destructiveHint, the description supplies the missing behavioral context: automatic save, verification workflow, inverse tool, and both error conditions. With an output schema present, it need not elaborate further on return structure.

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%, so all six parameters are already documented in the schema; the description adds no syntax, format, or path-resolution hints. Its only parameter-adjacent content is echoing the return fields (nodePath, signal, targetNodePath, method), which is confirmation rather than added semantics. Baseline 3 applies.

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 ("Remove a signal connection between two nodes") plus the persistence consequence ("persist the change in the .tscn"). It also names the sibling tools that bracket it (get_node_signals for verification, connect_signal for undo), so an agent can pick it out of the catalog without opening a 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 explicit preconditions ("Use get_node_signals first to confirm the connection exists"), the inverse operation ("connect_signal puts it back"), and two hard failure conditions (missing connection, live runtime session). The when-not-to-call case is covered by the runtime-session error note.

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