auto_mix

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

Annotations only carry destructiveHint=true, and the description adds substantial behavioral context beyond that: it performs a destructive multi-step mix, but saves a copy of the project first when it has a file, and deliberately leaves user-set EQ/compression/panning untouched. It also discloses resource behavior ('one render pass') and the -6 dBFS headroom outcome, which an agent needs to predict the effect.

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 purpose is front-loaded and the final sentence usefully points at verification tools, but the core is a sprawling run-on sentence enumerating every mixing step. Much of that enumeration is closer to internal implementation detail than selection-relevant information, so it is denser than it needs to be.

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?

For a complex, destructive multi-step tool it covers the essentials: what is changed, what is protected, the safety copy, and the recommended follow-up checks; dry_run is left to the schema. Without an output schema the description carries the return burden, and it only implies reporting via the schema's dry_run text rather than describing normal results, which keeps it from a 5.

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 100%, so the schema already documents style, reverb, dry_run, end_bar, sidechain and start_bar, setting the baseline at 3. The description echoes behavior associated with some flags (reverb return, sidechain ducking under kick, measuring a range) but adds no format or syntax detail beyond the schema, and never mentions 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 names a specific verb+resource ('A whole first mix in one call') and enumerates the concrete operations performed, from per-track measurement through role assignment, leveling, high-passing, compression, panning, reverb send, sidechain ducking and headroom. An agent can instantly distinguish it from narrow siblings like add_vocal_chain, setup_sidechain or master_to_target.

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?

It provides clear workflow context by routing the agent to verification tools ('Then check it: show_spectrogram, check_vocal_clarity, compare_mix_to_style') and states a preservation rule for already-configured tracks. It never says when NOT to use it (e.g. instead of the single-purpose mixing siblings), so it stops short of full when/when-not guidance.

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