Run a single Godot scene, replacing any previous run while keeping the final debug output for inspection.
Run one scene; replaces the previous run and retains final debug output.
| Name | Required | Description | Default |
|---|---|---|---|
| headless | No | ||
| scenePath | Yes | Relative or res:// PackedScene path | |
| sessionId | No | Explicit process/debug session handle; required for follow-up tools on MCP 2026-07-28 | |
| timeoutMs | No | ||
| projectPath | Yes | Godot project directory |
Changes observed during successful MCP inspections.
v0.6.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds two useful traits beyond the annotations: the prior run is discarded and final debug output is retained (linking naturally to get_debug_output). It omits how the run is bounded (timeoutMs default/blocking), what headless changes, and the fact that sessionId is needed for follow-up tools – meaningful gaps for an openWorld, non-destructive-but-stateful process launch.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single front-loaded sentence with no filler. It is terse rather than padded, though the brevity is the source of the gaps elsewhere.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 5-parameter process-launching tool with no output schema and open-world behavior, the description should cover headless/timeout semantics and the sessionId handoff. Neither is present, leaving the agent to reverse-engineer behavior from sibling tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is only 60%; headless and timeoutMs have no schema description at all, and the description supplies no meaning for them either. Nothing in the description clarifies the sessionId follow-up requirement or path formats beyond what the schema already says.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb+resource ("Run one scene"), which separates it from run_project and launch_editor. It doesn't differentiate itself from the closest siblings run_scene_test and run_playtest, so it stops short of a 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
"Replaces the previous run" implies this is for a fresh single-scene execution, but the description never says when to prefer it over run_scene_test, run_playtest, or run_project, nor any prerequisites. Usage is left to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.