Skip to main content
Glama

playtest

Automate playtesting in Unity by observing game state, simulating taps and UI clicks, capturing screenshots, and interacting with game objects to validate behavior.

Instructions

Autonomous playtesting: observe game state, simulate taps, click UI elements, capture screenshots, and interact with game objects during Unity play mode

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
xNoScreen X coordinate for tap action
yNoScreen Y coordinate for tap action
argsNoComma-separated method arguments for interact action
col1NoSource column for swap_tiles action (0-based)
col2NoTarget column for swap_tiles action (0-based)
nameNoUI element name for click_ui action (deep search across all canvases)
row1NoSource row for swap_tiles action (0-based)
row2NoTarget row for swap_tiles action (0-based)
textNoText to search for in wait_for 'text' condition
end_xNoEnd screen X for swipe action
end_yNoEnd screen Y for swipe action
valueNoValue to set for Slider (float) or InputField (text) in click_ui
widthNoScreenshot width in pixels (default 540)
actionYesobserve: full game state snapshot (scene, UI text, buttons, camera) | tap: simulate tap at screen coordinates (tries UI, Physics2D, Physics3D) | click_ui: click a UI element by name (Button, Toggle, Slider, InputField) | screenshot: capture camera view to PNG file | get_ui: list all active UI elements with types and state | wait_for: check if a condition is met (scene, text, object, playing, paused) | interact: call a method on a game object component via reflection | get_grid: read tile grid state (frequencies, positions, static status) for match-3 games | swap_tiles: swap two tiles by grid coordinates (col1,row1 <-> col2,row2) | swipe: simulate swipe gesture via screen coordinates (start_x,start_y -> end_x,end_y)
heightNoScreenshot height in pixels (default 960)
start_xNoStart screen X for swipe action
start_yNoStart screen Y for swipe action
conditionNoCondition type for wait_for: scene, text, object, playing, paused
sceneNameNoExpected scene name for wait_for 'scene' condition
methodNameNoMethod to invoke for interact action
objectNameNoGameObject name for wait_for 'object' condition
objectPathNoGameObject path for interact action (e.g. 'GameManagers')
componentTypeNoComponent type name for interact (e.g. 'GameFlowManager')
Behavior3/5

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

Annotations indicate readOnlyHint=false, consistent with mutation. The description adds no extra behavioral context (e.g., side effects, error conditions); it merely lists actions already detailed in the schema.

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?

Single sentence efficiently captures the tool's purpose and capabilities, though it could be slightly more structured or bulleted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema, so description could explain return values or state after actions. It adequately describes the tool's scope but lacks completeness for a complex 23-parameter tool.

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 coverage is 100%, so baseline is 3. The tool description adds no further parameter details beyond the schema's per-action descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool is for autonomous playtesting in Unity play mode, listing core actions. It distinguishes from sibling tools like play_mode or scene management by focusing on in-play interactions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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

No explicit guidance on when to use this tool versus alternatives like find_gameobjects or execute_code. The description omits context for when playtesting is appropriate.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/joel-wehr/unity-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server