bounce

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

Goes well beyond the annotations: discloses that the song plays audibly, that transport/loop/metronome/arm states are restored, that same-named files are replaced, and that temporary tracks are created and removed on polling. The destructiveHint annotation is reinforced with concrete detail about what is overwritten and cleaned up.

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?

Front-loads the core purpose, then per-parameter details, then the mandatory polling workflow. Dense but every clause is load-bearing; slightly run-on but appropriately sized for a 7-parameter tool with no schema descriptions.

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?

Complete for a mutation/export tool with no output schema: it explains the async job model, the required polling step, side effects, and output locations/defaults. Nothing an agent needs to invoke it correctly is missing.

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 formats for start/end ('bar.beat.sixteenth' or locator name), the end default behavior, tail units (beats, '1 bar', seconds), stems syntax ('all', names, indices, 'return:A'), include_returns, output_dir default and file-naming pattern.

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?

States a specific verb and resource ('Render the arrangement to WAV in real time') plus scope ('the master plus optional stems'), which is concrete enough to distinguish from siblings like export_audio. An agent knows exactly what operation this performs.

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?

Gives clear workflow context: the returned job must be polled via get_bounce_status(wait=50) and 'polling is required', plus a concrete example invocation. It does not explicitly contrast with the sibling export_audio, so the when-to-use-vs-alternative condition is left implicit.

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