create_scene

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

No annotations are provided, so the description must carry the full burden. It states that creating a scene is a mutating action but does not disclose side effects, such as whether an existing scene is replaced or reset. It also omits any details about persistence or relationships to other scene operations. The warning about standalone scripts is procedural, not behavioral.

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 very short: two sentences plus an internal IMPORTANT note. It is front-loaded with the core purpose. The extra instruction is relevant and earns its place, though it could be seen as a policy note rather than tool-specific detail. Overall, it is efficient and not bloated.

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 an output schema present and four well-documented parameters, the tool is simple. However, the description does not explain how create_scene fits into the broader workflow (e.g., that it should likely be called before adding objects) or what the output contains. It provides enough for its immediate use but lacks guidance on orchestration with sibling tools.

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?

The input schema has 100% coverage, with each parameter (fps, resolution, frame_height, background_color) described with defaults. The description adds no extra nuance beyond 'configuration' and does not clarify parameter interactions. Per the rubric, full schema coverage yields a baseline of 3, and there is no added value to raise it.

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's action: 'Create a new manimgl scene with the given configuration.' The verb 'Create' and resource 'manimgl scene' make the purpose specific. This distinguishes it from sibling tools like add_* or render_scene, which operate on an existing scene.

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 includes an IMPORTANT rule: 'Always use MCP tools for scene operations. Do NOT write or execute standalone manim scripts.' This provides high-level workflow guidance but does not explicitly state when to use create_scene versus alternatives like clear_scene or get_scene_info. It implies create_scene is the starting point but does not clarify prerequisites or sequencing.

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