Create 3D audio-reactive scene

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

Beyond annotations (readOnlyHint false, openWorldHint true, destructiveHint false), the description discloses specific behavioral traits: creates a baseCOMP under parent_path, includes Camera/Light/Render TOP and Null TOP output, exposes Sensitivity/Zoom/Spin controls, warns about a macOS microphone-permission prompt, and describes the return payload (summary + JSON block with paths, errors, warnings, preview image). No contradiction with 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 well-structured and front-loaded with the core purpose, then systematically explains modes, components, controls, sources, and return value. Every sentence adds information; there is no filler or repetition of schema field text. Despite its length, it remains appropriately concise for a complex build 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?

This is a complex tool with 9 parameters, no output schema, and only basic annotations. The description fully compensates by covering the generated node structure, source options, permission caveat, exposed controls, return format, and fallback behavior. It provides enough context for an agent to invoke the tool correctly and interpret the result.

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?

Input schema covers 100% of parameters with detailed descriptions, so baseline is 3. The description adds extra semantic value beyond schema: 'bass_pulse' is described as the guaranteed-visible fallback, 'oscillator' is 'handy for testing without any device permission', and it explains the FFT spectrum mapping context. These nuances help parameter selection beyond what the schema already provides.

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 3D scene that reacts to sound') and clearly distinguishes this from the sibling create_audio_reactive (2D counterpart). It also differentiates from other 3D creation tools like create_3d_scene by focusing on audio reactivity and FFT-driven geometry.

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_audio_reactive) for 2D spectrum visuals and provides guidance on choosing between modes (instanced_bars vs bass_pulse fallback) and sources (device/file/oscillator/existing_chop), including when oscillator is handy for testing without device permission. This is clear when-to-use and alternative guidance.

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