transcribe_drums

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

With no annotations provided, the description carries the full burden and does so well. It discloses async background execution, possible model-weight downloads on first use, local-only audio handling, no project mutation, and the fact that tom and cymbal articulations are estimates. This is rich, honest behavioral context beyond a simple one-line summary.

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?

Six sentences, each earning its place: the main action is front-loaded, followed by source selection, workflow, prerequisites, side effects, and a quality caveat. There is no redundancy or filler.

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 tool with no output schema and no annotations, the description covers the key workflow, return value, prerequisites, and safety profile. The main gap is parameter semantics: device, threads, and separate are not explained, and source-parameter precedence is unclear. Still, the description is substantially complete for invoking the tool correctly.

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 the source-selection concept ('one selected audio item or a named source track/item') but does not describe the semantics of device, threads, or separate, nor which source parameter takes precedence. The agent is left guessing about meaningful options like cuda vs cpu, thread count, and what 'separate' actually controls.

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: starting a local audio-to-drum-MIDI analysis in a background worker using an audio item or named source track/item. It clearly distinguishes itself from the related get_drum_transcription and insert_drum_transcription tools by framing itself as the initiation step.

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 context: use a selected audio item or named source track/item, expect a job_id, poll get_drum_transcription, then insert_drum_transcription. It also names prerequisites like the transcription environment and ffmpeg. However, it does not explicitly say when not to use this tool or compare it with alternative analysis tools such as analyze_track or compare_tracks.

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