Preview Render (Viewport, Constant Lines)

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

With no annotations provided, the description carries full responsibility for behavioral disclosure—and it excels. It discloses that the active editor view is temporarily switched to Constant Shading (Lines), that the render is built freestanding and never inserted, and that BaseDraw/camera/time/take state is restored in finally. It also states it returns a base64 PNG inline. This is exemplary transparency about side effects and restoration behavior.

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 dense but well-structured. It opens with the core purpose ('Quick agent-friendly verification render'), then details the renderer and state restoration, followed by output format, and finally the view/camera/save_path options. Every sentence adds value, though it is slightly longer than necessary for the amount of detail (e.g., the try/finally detail could be implied). No fluff.

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?

Given the tool's complexity (7 parameters, no required, no output schema, no annotations), the description is remarkably complete. It covers the return format (base64 PNG), the side effects (state restoration), the mutual exclusivity of view/camera, and the optional disk write. An agent has everything needed to invoke it correctly without additional context.

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?

Although schema coverage is 100% (all parameters documented), the description adds meaningful semantic context beyond the schema. It explains that 'view' presets place a temp camera looking at scene bounds and that it is removed in finally, that 'camera' is mutually exclusive with a non-'current' view, and that save_path still returns the base64 PNG inline. This goes beyond the raw schema definitions and enriches agent understanding.

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 clearly states the tool does a 'quick agent-friendly verification render' using the Viewport renderer with Constant Shading (Lines). It explicitly distinguishes itself from a full render (independent of active RenderData, freestanding) and even contrasts with siblings like 'render' by being a lightweight preview. The verb 'render' with the resource 'preview' is precise and the styling detail (sketch-style and fast) further clarifies purpose.

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 establishes clear context: it is for quick verification, not final output, and it is independent of the active RenderData. It explains the view/camera options and the save_path for disk output. However, it does not explicitly state when NOT to use it or name a specific alternative (like 'render' for final renders). The implied usage is strong but lacks explicit exclusions.

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