blender_add_primitive

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

Annotations are all false/unspecific, so the description carries the behavioral burden. It discloses that the tool creates in the scene and returns a full description, and the example illustrates response-affecting options like shade_smooth. It does not clarify selection effects, naming defaults, or the exact shape of the returned description, but there is no contradiction.

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?

One main sentence plus a compact, relevant example. The core action and return behavior are front-loaded, and every phrase in the example earns its place by clarifying real usage.

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?

Adequate for a simple primitive-adding tool: the example and schema defaults cover the main call pattern. But with 10 optional parameters, no output schema, and no explicit return-shape description, an agent still has to infer how materials, collections, and response_format interact, so the description is not fully complete.

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 example adds real meaning beyond the schema by showing how type, parameters, and shade_smooth combine for a torus, and it introduces primitive-specific parameter keys (major_radius, minor_radius, segments). With 60% schema coverage, this usefully compensates for schema gaps, although not every parameter is illustrated.

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 concrete action ('Add') and resource ('mesh primitive to the scene'), and adds that it returns a full description. It is not a tautology and is distinguishable from generic siblings, though it does not explicitly differentiate from blender_create_mesh.

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 action itself implies when to use it (when a mesh primitive is needed), and the torus example provides a concrete invocation pattern. However, it gives no explicit guidance about when not to use it or which sibling to prefer (e.g., blender_create_mesh for custom meshes).

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