create_cushion

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

With no annotations, the description carries full burden. It adds genuinely useful behavioral context beyond the schema: origin is at the bottom centre and it returns top_z for stacking. However, it omits side-effect behavior (whether it adds the object to the scene, material defaults, or scene prerequisites) that an agent would want for a creation tool.

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 dense, front-loaded sentences that waste no words; the geometry concept leads and the origin/return note follows. Slightly terse for the tool's complexity, but every clause earns its place.

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 13-parameter creation tool with no annotations, no output schema, and only 62% schema coverage, the description is thin. It covers purpose, geometry, and origin/return, but leaves usage selection and mutation/side-effect behavior unspecified, so an agent still has gaps to fill.

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 coverage is 62%, and the description compensates meaningfully by explaining the geometry concepts behind the loosely documented params: bulging sides (bulge), crowned faces (crown), rounded-rectangle plan (corner), seam piping (piping), and optional buttons (tufted). It adds visual semantics the bare param names lack, though it stops short of units or value ranges.

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 what is produced (upholstered soft goods like a real cushion) and lists distinguishing geometric features (rounded-rectangle plan, bulging sides, crowned faces, seam piping, buttons). This lets an agent recognize it as a specialized cushion builder rather than a generic primitive, though it never explicitly contrasts itself with siblings like create_primitive or create_loft.

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?

No when-to-use guidance is given: nothing tells the agent when to reach for create_cushion versus create_primitive, create_loft, or create_extrusion, nor any preconditions. Usage must be inferred entirely from the geometry description.

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