auto_mix

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

The description explicitly discloses the mutating behavior of dry_run=False ('APPLY the volume/pan corrections to the Live set (mutating!)'), complements the destructiveHint=true annotation. It also discloses external dependencies (Ableton Live, AbletonOSC) and the offline capability of dry runs. It could add details on whether the operation is reversible or what happens to the Live set state, but the description plus annotations give a solid picture.

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 with a concise one-line purpose, an Args section, a Returns line, and a clear usage directive. Every sentence earns its place. Slightly verbose with the line breaks and formatting, but information-dense and front-loaded with the purpose statement. Not quite maximal efficiency but close.

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 an output schema present and 100% parameter coverage, the description needs less. It covers the core safety protocol (dry_run first), external dependencies, and output shape. For a mutating tool with destructiveHint=true, the key gap would be whether corrections are reversible or how the user validates results post-application, but given the strong annotations, schema, and output schema, it's reasonably complete.

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 the bar is set at baseline 3. The description adds value by explaining the render_dir semantics ('one WAV per track, bounced from Ableton'), clarifying pattern as the file-matching glob, and grounding dry_run as a safety toggle returning recommendations vs applying changes. It reinforces but also enriches schema descriptions, particularly for render_dir and dry_run.

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 'Auto-mix rendered tracks toward a musical style' with a specific verb+resource. It lists the action (auto-mix), the inputs (rendered WAV tracks), and the output (per-track corrections and master notes). It distinguishes itself from siblings like analyze_render_dir (which analyzes) and preview_mix (which previews) by being the action tool that applies corrections.

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 directs usage: 'Call with dry_run=True first to review the recommendations; only use dry_run=False to apply them to the Live set.' It also states prerequisites (Ableton Live + AbletonOSC for dry_run=False) and that the dry run works offline. This provides clear when-to-use and when-not-to-use guidance, plus the two-step safety protocol.

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