Skip to main content
Glama
Beckett — MCP for Godot

Beckett — MCP for Godot

by beckettlab

play_scene

Launch a Godot scene—specific, current, or main—then wait for play start and read logs; queue runtime property writes and run muted off-screen to keep working.

Instructions

Play a scene in the editor. 'scene' (res://) plays a specific scene; current=true plays the open scene; otherwise the project's main scene. Then wait_until condition=play_started, and logs_read for errors. on_ready queues runtime property writes applied the moment the new game connects — the restart boundary batch_execute cannot cross. quiet=true plays muted and off-screen so the person keeps working. Script errors do not pause the game (4.5+): game_logs has them. on_ready shape, retries, what quiet does per run mode: help(tool="play_scene").

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": "play_scene"
  }
}

Input Schema

NameRequiredDescriptionDefault
quietNomute the game and park its window off-screen without focus, so the person keeps working
sceneNores:// path; omit for main/current
currentNo
on_readyNoproperty writes applied once the game connects (shape in help)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.17.0
    • addedInput schema / properties / quiet
      Added value: +{
      +  "description": "mute the game and park its window off-screen without focus, so the person keeps working",
      +  "type": "boolean"
      +}
  2. Changed1 schema field changedv1.14.0
    • changedInput schema / properties / on_ready / description
      Previous value: -"property writes applied once the game connects: [{path, property, value}, ...] (path may be a name/class selector, same as runtime_set_property)"New value: +"property writes applied once the game connects (shape in help)"
  3. Addedv1.12.1
  4. Removedv1.10.0
  5. First observedv1.0.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations only cover the safety profile (readOnly=false, destructive=false, openWorld=false); the description adds real behavioral context beyond them: script errors do not pause the game on 4.5+, quiet plays muted and off-screen, and on_ready is applied at the moment the new game connects — the restart boundary batch_execute cannot cross. It does not state what happens to an already-running scene, and it defers retry/on_ready details to help(), which is a modest gap.

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 the core action and selection logic, then workflow, then option semantics, ending with a signposted deferral. The telegraphic density ('on_ready shape, retries, what quiet does per run mode: help(...)') is efficient, though the compressed phrasing costs a little readability.

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?

No output schema exists, and the description compensates by telling the agent where results surface — game_logs and logs_read — and by naming the wait_until condition to gate on. The remaining gaps (on_ready shape, retries, quiet per run mode) are acknowledged and routed to help(), so the agent knows what it does not know rather than being silently under-informed.

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 coverage is 75% and the undocumented parameter is current, which the description resolves ('current=true plays the open scene'). It also adds meaning over the schema for on_ready (writes applied at connect, explicitly distinct from batch_execute) and quiet (per-run-mode behavior). The exact on_ready shape and retry semantics are pushed to help(), leaving something on the table.

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 ('Play a scene in the editor') and then disambiguates the three selection modes — res:// path, current=true, default main scene — so an agent can distinguish it from open_scene, stop_scene, and get_play_state 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 Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete workflow sequencing: play, then wait_until condition=play_started, then logs_read for errors, and points at help() for deeper semantics. It also explains the quiet=true case as the option for when a human is working. It never explicitly names a sibling tool it is an alternative to (e.g. open_scene vs play_scene), which keeps it below a 5.

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