create_bus

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

Annotations already declare a non-destructive, non-idempotent, closed-world write. The description goes well beyond that by disclosing monitoring/input settings ('In', 'No Input'), placement at the end of the set, the routing side effect, the uniqueness constraint, the audio-output prerequisite for sources, and that reverting requires two undo steps. This is rich behavioral context that annotations alone do not provide.

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 front-loads the core definition of a bus, then layers constraints, routing guidance, and an example call. It is dense and every sentence carries useful information, though the long opening sentence with nested parentheticals could be split for easier parsing.

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 no output schema, the description covers creation mechanics, routing, post-creation mixing, prerequisites, and undo behavior thoroughly for a write tool. It omits what the tool returns (e.g., the new track identifier) and the accepted color encoding, but those are secondary for correct invocation.

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 0%, so the description must compensate. It explains that 'name' must be unique and that 'sources' are tracks whose output is routed into the bus (requiring audio output), and the example demonstrates 'color' with a hex string. It does not clarify that color accepts either an integer or a string, nor whether sources accept track names, indices, or both, but it covers most parameter semantics.

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 states a specific verb and resource ('Create a bus') and immediately clarifies that it creates a special audio track acting as Live's substitute for group tracks, with source outputs routed into it. This distinguishes it from sibling tools like create_track by describing the distinctive routing behavior. An agent can tell what the tool does without opening the schema.

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 gives concrete usage context: mix the bus like any track with set_mixer or add_device, name must be unique, sources need audio output (MIDI tracks need an instrument), and reverting takes two undo steps. It does not explicitly state when to prefer this over create_track or duplicate_track, but the operational guidance is clear and actionable.

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