create_primitive

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

No annotations are provided, so the description carries the burden of behavioral disclosure. It does provide useful context about which parameters apply to which primitive types (e.g., size for cube/plane/monkey, radius for spheres), which is beyond the schema. However, it does not disclose typical creation behaviors like adding the object to the scene, default naming, return values, or any side effects. This is a moderate gap given the lack of annotations.

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 a single, efficient sentence that front-loads the purpose and immediately provides the list of types and parameter mappings. Every part contributes to the agent's understanding, with 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?

With 11 parameters, no output schema, and no annotations, the description is insufficiently complete. It omits explanations for several parameters (name, scale, location, rotation, collection, text) and does not describe expected behavior on success, return values, or potential side effects. The description covers the core primitive types but leaves critical operational details unaddressed, making it hard for an agent to use the tool correctly without additional assumptions.

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 low (approximately 45% – only type, size, radius, depth, and segments are mentioned). The description compensates by explaining which parameter applies to which primitive type, adding value beyond the schema. However, many parameters (name, text, scale, location, rotation, collection) are not described at all, leaving significant ambiguity. The description partially compensates but does not fully cover the gap.

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 a clear verb ('新建' = create) and resource ('基础物体' = basic object), and enumerates the specific primitive types supported (cube, plane, sphere, etc.). This distinguishes it from sibling tools like create_light, create_camera, and create_material, which create different resources. The purpose is unambiguous.

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 implies its use for creating any listed primitive, which is clear from the tool name and content. However, it does not explicitly state when not to use it or mention alternatives (e.g., 'for lights use create_light'). The context is sufficient for an agent to infer the appropriate scenario, but explicit exclusions are absent.

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