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

Goes well beyond the readOnly/destructive/openWorld annotations by disclosing tier gating (Plus users), credit consumption, rate limiting, the dual output modes (always a WebGL URL, conditionally a cached PNG), and explicitly that saving state is untouched. This is exactly the behavioral context an agent needs before invoking.

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, front-loaded with the core action before the conditional Plus/PNG caveat and the non-mutation guarantee. No filler or redundancy.

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?

There is no output schema, so the description must carry weight, and it partially does by describing the two return paths (URL and optional PNG). But with 6 undocumented parameters and no return-shape detail beyond what the image is, it is only adequate for a tool of this complexity.

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% across 6 parameters, so the description carries the full burden — yet it only explains includeImage. The meaning of model (ID, path, or inline data), view, imageSize, background, and language is left entirely unstated despite four of them being enums.

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+resource ('Preview a voxel model') and names the platform, so an agent knows this is a read-only preview operation. It implicitly contrasts with mutation siblings via 'does not modify a saved user project,' but never names export_voxel_model or inspect_voxel_model, which an agent might also consider for viewing a model.

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 conditional context for includeImage (Plus users only, credits, rate limits), which implies when the PNG path is available. However, there is no guidance on when to choose this tool over export_voxel_model or inspect_voxel_model for similar-looking tasks.

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