Create PBR scene

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

Annotations only state readOnlyHint=false and destructiveHint=false, so no contradiction exists. The description goes beyond by detailing exactly what is created ('a new baseCOMP under parent_path' with a full list of nodes), how env_color works without an HDRI file, what controls are exposed, and what the return payload contains (summary, JSON block, preview image). This is rich behavioral context not present in 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 relatively long but densely packed with essential information: main action, node list, alternative tool, controls, rotate behavior, and return format. It is front-loaded with the primary purpose and uses clear structural progression. While lengthy, every sentence earns its place for a complex scene-creation tool.

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 8 parameters and no output schema, the description carries the full burden of explaining return values and component creation. It comprehensively covers the entire scene graph, fallback behavior (no HDRI), exposed controls, and return payload (paths, errors, preview). It also provides an explicit fork to create_3d_scene, making it contextually complete for an agent to decide and invoke correctly.

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 100%, so baseline is 3. The description adds minimal parameter context beyond the schema: it mentions the exposed controls (Metallic, Roughness, BaseColor, Spin) and actions (rotate to show reflections), but these are already in the schema. It does not significantly deepen parameter understanding, so a 3 is appropriate.

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 opens with a specific verb+resource: 'Build a physically-based 3D scene' and enumerates exact components (Geometry COMP, PBR MAT, Environment Light, etc.). It clearly distinguishes itself from sibling 'create_3d_scene' by stating 'Use create_3d_scene instead for basic (non-PBR) shading or GPU instancing.' The verb 'Build' and 'Creates' precisely convey the action and outcome.

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 explicitly names the alternative tool ('create_3d_scene') and specifies when to use it ('for basic (non-PBR) shading or GPU instancing'). It also provides practical usage tips like 'set rotate to turn the object so its reflections move' and explains the env_color Constant TOP fallback, giving clear context for when this PBR-specific tool is appropriate.

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