Run a fail-fast sequence of Blender scene actions—create, transform, material, keyframe, render—then inspect the final scene.
Execute an ordered, fail-fast batch of allowlisted Codex3D Action objects, then inspect the final scene. Supports creation, transform, material, parenting, scene/world configuration, keyframes, render, and checkpoint actions.
| Name | Required | Description | Default |
|---|---|---|---|
| actions | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already reveal destructiveHint=true, and the description adds meaningful behavioral details: actions are ordered, fail-fast, and the tool inspects the final scene afterward. This goes beyond the annotations, though it doesn't cover partial-failure or rollback 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?
Two sentences with no filler, front-loading the core behavior and then summarizing supported action families. The category list is compact but slightly redundant with the schema enum, keeping this from a perfect score.
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 destructive tool with 16 action types, no output schema, and no per-action parameter definitions, the description is too sparse. It hints that the final scene is inspected but doesn't clarify the return format, failure behavior, or how to compose a valid batch action object.
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 description coverage is 0%, and the description does not explain how to construct valid parameters objects for any action type or what the metadata/description fields mean. It only lists supported action categories, which is too little guidance for the actions array parameter.
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 clearly states the tool executes an ordered batch of allowed Action objects and then inspects the final scene. This specific verb-plus-resource framing distinguishes it from the many single-action sibling tools like blender_create_primitive or blender_transform_object.
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 batch framing and the enumerated action categories imply this is for composing multiple actions in one ordered run, but the description never explicitly says when to prefer it over calling individual sibling tools or when not to use it. Usage guidance is mostly implied rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.