create_track

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

Annotations declare non-read-only, non-destructive, non-idempotent, closed-world, but the description adds real behavioral context beyond them: native devices are inserted directly while Max for Live/pack devices load through the browser, and new MIDI tracks can come up armed. It also states the return payload (ref, routing, arm state), which matters since no output schema exists.

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?

Dense but front-loaded, with a worked example at the end. Every clause carries parameter or behavioral information; the single long paragraph is slightly heavy but not padded.

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 5-param mutation tool with no output schema and 0% schema coverage, the description compensates fully: it documents all parameters, the device-loading path, the MIDI-track prerequisite, and the return fields.

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 0%, so the description carries the full burden and does: it defines kind values, index semantics (-1 = end, returns last), color format (0..69 or "#RRGGBB"), device name matching (case-insensitive, native vs browser-loaded), and name. This is more than the bare schema 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?

Opens with a specific verb+resource ('Create a track') and immediately enumerates the kind values, distinguishing it from create_bus/create_scene. An agent can tell exactly what this tool produces 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?

Provides concrete usage conditions: instruments and MIDI effects require a MIDI track, returns always go last, index=-1 means end, and devices can be inserted by name. It does not explicitly point to siblings (e.g. create_bus, duplicate_track) as alternatives, so it falls just short of a 5.

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