create_metaball

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

With no annotations, the description carries the behavioral burden and does it well: 500-element cap, default single ball, the rule that elements closer than their radii merge, negative elements carving, and a stated return shape. It omits scene/collection placement and whether the new object becomes selected/active, which matters for chained object-creation workflows.

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?

Front-loaded one-line summary, then intended use, then a structured Args block, then Returns. The length is justified by five parameters including a nested schema; no sentence is filler.

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?

Return value is covered, parameters are fully explained, and the conversion path to editable geometry is stated. The remaining gap is context-of-creation (target collection, selection state, mode requirements) for a tool in a large scene-authoring surface with zero annotations.

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%, so the description must compensate, and it does: every parameter gets type, default and meaning, including the counterintuitive threshold ('lower is fatter') and resolution range endpoints. The nested elements dict is documented field-by-field (type enum, relative location, radius default 1, stiffness 0-10, size half-extents, negative), which the schema renders as an untyped free-form object.

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?

Specific verb+resource ('Create a metaball') immediately followed by a plain-language definition of the object type ('soft elements that melt into one smooth surface'). This distinguishes it from hard-surface creation siblings such as create_polygon_prism, create_lattice, or create_object without the agent needing to open any schema.

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 concrete use cases ('organic blobs, liquid drops, quick character blocking') and routes the agent to convert_object(target="MESH") for the downstream step. It stops short of explicit exclusions (e.g. 'for hard-surface primitives use create_polygon_prism'), so it is clear context rather than a full when/when-not map.

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