Capture the rendered frame of a running windowed game as an image plus its size. Requires a session started with windowed=true, since headless games draw no pixels.
Capture what a windowed game is drawing. Returns: the image, with its size. Needs a session started with windowed=true; a headless game has no pixels.
| Name | Required | Description | Default |
|---|---|---|---|
| session_id | No | Session from runtime_run. Required only when several games run. |
Changes observed during successful MCP inspections.
v1.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavioral context beyond that: the windowed=true session requirement and the headless failure mode. It also states the return shape (image plus size), which matters because there is no output schema.
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 with the action front-loaded, followed by the return value and the prerequisite. Nothing is redundant or padded.
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, the description correctly explains what comes back (the image and its size), and it covers the failure precondition. For a one-parameter read-only tool, nothing an agent needs to call it successfully 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% and the single session_id parameter is documented in the schema. The description adds a related constraint (the session must be windowed), which helps interpretation but does not add syntax or format detail beyond what the schema already provides, so the baseline 3 applies.
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 and resource: 'Capture what a windowed game is drawing.' An agent immediately knows this returns a screenshot of the running game. It does not explicitly name sibling tools to differentiate from, but the runtime_* family makes the domain unambiguous.
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?
Gives a concrete prerequisite: the session must have been started with windowed=true, and a headless game has no pixels. This is exactly the condition an agent needs to avoid a failed call. It stops short of naming an alternative or exclusion against siblings, but no competing screenshot tool exists.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.