Cancel a queued job you started through the API or MCP and refund its credits. Jobs that are already running cannot be canceled (409). Returns the canceled job. This is free (no credits). Requires an API key (user scope).
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full disclosure burden and does so thoroughly. It states the side effect (credit refund), the cost (free), the authentication requirement (API key with user scope), the failure mode (409 for running jobs), and the return value (the canceled job). This is comprehensive for a one-parameter operation.
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?
The description is four sentences, each conveying necessary information: the action, the constraint, the return value, and the cost/auth requirements. There is no filler or repetition, and the main action is front-loaded.
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?
Given the low complexity (1 simple parameter, no output schema, no annotations), the description provides everything an agent needs to invoke the tool correctly: what it does, when it applies, what can go wrong, what it costs, and what it returns. No critical behavior is left unexplained.
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?
Although the schema only defines 'id' as a string with no description, the tool description implies that the id identifies the queued job to cancel. This adds meaningful context beyond the schema, even though it does not explicitly say 'id is the job identifier'. For a single obvious parameter, this is adequate, with minor room to state the source of the id.
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?
The description states a specific verb ('Cancel'), a resource ('a queued job you started through the API or MCP'), and a clear effect ('refund its credits'). It also distinguishes itself from siblings like getApiJob and listApiJobs by targeting cancellation only, with no ambiguity.
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?
The description clearly indicates when to use the tool: for queued jobs that the user started, not for running jobs. It explicitly warns that running jobs cannot be canceled and will return a 409, providing a key exclusion. It does not name alternative tools, but the context makes the intended use clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools pair a clear action and asset type (create3DModel, editVideo, removeBackground), and overlapping pairs such as animateSprite vs transferMotion vs animateSpriteKeyframes are carefully differentiated by input mode. The main friction is listApiJobs vs listGenerations, which both return generation history from slightly different scopes.
The set is overwhelmingly consistent camelCase verb+noun (create*, edit*, list*, animate*, cancel*), with only minor deviations like generatePose/generateWithStyle alongside createImage and the slightly awkward validateApiKeyEndpoint. There is no chaotic mixing of conventions.
At 31 tools this exceeds the 25+ threshold for 'too many', even though the multimodal game-asset scope explains much of the breadth. Agents face a large selection surface with many generation variants across 3D, sprites, images, audio, and video.
Core workflows are covered: image-to-3D plus rigging and animation, sprite pose/rotation/animation/editing, image create/edit/style/background-removal, video create/edit/upscale, and audio SFX/ambiance/music/voice. Minor gaps remain, such as no image upscaler and no individual asset retrieval or deletion.
