Skip to main content
Glama

stop_project

Destructive

End the active Godot runtime session, remove its bridge, and stop a spawned game or detach from an attached one without killing it; other sessions continue.

Instructions

End the current session now and remove the bridge, cutting off a runtime call in progress. A spawned Godot is stopped; an attached one is detached, not killed. Other sessions keep running; none becomes current. Also frees a spawned game that exited by itself (alreadyExited). Returns: projectPath, message, sessionMode, externalProcessPreserved, alreadyExited, exitCode, killUnconfirmed, finalOutput, finalErrors; warnings leads if the kill or cleanup was unconfirmed. Errors if nothing is running.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "stop_project"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Output Schema

NameRequiredDescriptionDefault
pidNoPid the unconfirmed kill was sent to.
messageYes
exitCodeNo
warningsNo
finalErrorsYesNull in the same cases as finalOutput.
finalOutputYesCondensed to the diagnostic lines. Null when no logs are held: an attached session captures nothing, and a record that kept only a finished profiler capture gave its logs to the earlier stop.
projectPathYes
sessionModeYes
alreadyExitedYes
killUnconfirmedNoPresent and true when the kill was sent and the process did not report its exit in time: it may still be running. warnings names the pid.
externalProcessPreservedYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed11 schema fields changedv4.0.1
    • addedOutput schema / properties / finalErrors / description
      Added value: +"Null in the same cases as finalOutput."
    • changedOutput schema / properties / finalErrors / type
      Previous value: -"array"New value: +[
      +  "array",
      +  "null"
      +]
    • addedOutput schema / properties / finalOutput / description
      Added value: +"Condensed to the diagnostic lines. Null when no logs are held: an attached session captures nothing, and a record that kept only a finished profiler capture gave its logs to the earlier stop."
    • changedOutput schema / properties / finalOutput / type
      Previous value: -"array"New value: +[
      +  "array",
      +  "null"
      +]
    • addedOutput schema / properties / killUnconfirmed
      Added value: +{
      +  "description": "Present and true when the kill was sent and the process did not report its exit in time: it may still be running. warnings names the pid.",
      +  "type": "boolean"
      +}
    • removedOutput schema / properties / mode
      Removed value: -{
      -  "type": "string"
      -}
    • addedOutput schema / properties / pid
      Added value: +{
      +  "description": "Pid the unconfirmed kill was sent to.",
      +  "type": "number"
      +}
    • addedOutput schema / properties / projectPath
      Added value: +{
      +  "type": "string"
      +}
    • addedOutput schema / properties / sessionMode
      Added value: +{
      +  "enum": [
      +    "spawned",
      +    "attached"
      +  ],
      +  "type": "string"
      +}
    • addedOutput schema / properties / warnings
      Added value: +{
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / required
      Added value: +[
      +  "projectPath",
      +  "message",
      +  "sessionMode",
      +  "externalProcessPreserved",
      +  "alreadyExited",
      +  "finalOutput",
      +  "finalErrors"
      +]
  2. Changed2 schema fields changedv3.6.0
    • addedOutput schema / properties / alreadyExited
      Added value: +{
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / exitCode
      Added value: +{
      +  "type": [
      +    "number",
      +    "null"
      +  ]
      +}
  3. Addedv3.1.1
  4. Removedv3.0.0
  5. Addedv1.0.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare destructiveHint=true, and the description goes well beyond that: it discloses that only the current session ends, that no other session becomes current, that attached processes are detached rather than killed (externalProcessPreserved), and that a kill or cleanup failure surfaces as a leading warning rather than a silent success. This is exactly the mutation-scope and irreversibility context an agent needs.

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 action and its scope are front-loaded in the first sentence, and the spawned/attached distinction follows immediately while it is relevant. The closing enumeration of nine return fields is somewhat redundant given the output schema, but the note that warnings "leads" when the kill is unconfirmed carries ordering information the schema does not.

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 zero-parameter destructive teardown with an output schema present, the description supplies everything still missing: what is destroyed versus preserved, the effect on sibling sessions, the no-op error case, and how unconfirmed kills are reported. Nothing an agent needs in order to call it safely is absent.

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?

The tool takes zero parameters, so there is no parameter meaning to add and the baseline of 4 applies. Nothing in the description misrepresents or over-explains the empty input.

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?

"End the current session now and remove the bridge" pairs a specific verb with a specific resource, and the following clauses differentiate spawned (stopped) from attached (detached, not killed) runtimes. An agent can tell exactly what state change this tool performs without consulting any sibling schema.

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 gives clear conditions for use — terminating a session, including one cutting off an in-progress runtime call, and cleaning up a spawned game that exited by itself. The precondition "Errors if nothing is running" further narrows when it applies. It stops short of naming explicit alternatives (e.g., profiler-specific teardown), so it is strong but not a full when/when-not routing statement.

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