audio_transcribe

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

Beyond the readOnly/idempotent annotations, it discloses that the call is asynchronous ("Returns a job"), what the job result contains (notes in beats at project tempo plus detected length), and the permissions prerequisite. The main remaining gap is that it never says how to retrieve the job, leaving the agent to infer jobs_get/jobs_wait.

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?

Four dense sentences with no filler; the core transformation and input options are front-loaded, followed by output shape, then the permission caveat. Every clause carries actionable information.

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 does the work of explaining the job/result model and the note format, which is what an agent needs. The one omission is the job-retrieval path (jobs_get/jobs_wait) and whether polling or waiting is expected.

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 100%, so the baseline is 3, but the description adds genuine meaning the schema lacks: path and slot are alternative input routes rather than independent settings, and the enum values are glossed (poly = chords, melody = one line, bass). It does not touch min_ms, sustain, or sensitivity, which are left to the schema.

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 opening clause states a concrete transformation (audio to notes) and names the engine (Basic Pitch), then enumerates the two input sources (file path or session slot) and the three modes. An agent can distinguish this from audio_import or audio_split_stems purely from the text, 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 clarifies input selection (a file path OR a track+slot pair) and the prerequisite that file paths require file access enabled in Settings / AI Create. It also points forward to clips.write_midi as the consumer of the result, which implies the intended workflow. It stops short of explicit exclusions such as when to prefer audio_import or clips_generate_melody instead.

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