Run the game

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

Annotations declare readOnly=false, destructive=false, openWorld=false, but do not convey that the process remains running asynchronously. The description adds this crucial trait ('the game keeps running') plus the fact that output is only the first few seconds, which meaningfully shapes agent behavior.

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?

Three tight sentences, front-loaded with the primary action and scoping, followed by the continuation/cleanup routing and the script variant. No filler.

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?

With no output schema present, the description still summarizes the return ('the output and any errors') and the ongoing-process model. For a six-param tool with full schema coverage and no required params, nothing essential is missing.

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 100%, so all six parameters are already documented in the schema. The description adds only modest framing (scene vs SceneTree script) beyond what the parameter descriptions provide, so the baseline 3 is appropriate.

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 (Run) and resource (the project or one scene), and explicitly names the sibling tools get_debug_output and stop_project. An agent can distinguish it from launch_editor or create_scene without opening any schema.

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?

Clear context for use: run the project/scene, then use get_debug_output for continued output and stop_project to close. It also notes the SceneTree-script variant (e.g. headless test script). It lacks an explicit when-not-to-use or a comparison to launch_editor, so it stops short of the top score.

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