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

No annotations are provided, so the description carries the full behavioral burden. It does disclose the key output behavior (returns two stems: isolated vocals and instrumental) and that it is equivalent to process_audio with task_type='2stems', which is useful. However, it omits that processing is likely asynchronous (implied by siblings check_task_status/check_separation_status), any credit cost, or how/where to retrieve the resulting stems.

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-loaded with purpose and equivalence, then use cases, then parameters — appropriately sized with no filler. The Args block is slightly redundant formatting, but since schema coverage is 0% it earns its place rather than duplicating structured data.

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?

No output schema exists and the description does explain the two returned stems, which covers the main return-value need. Still, for a processing tool surrounded by status/credit siblings, it lacks the workflow context (async polling, where results are fetched, cost) an agent would need to complete the task end-to-end.

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, and it does: it explains that source_key comes from upload_audio or get_upload_url and that format accepts 'mp3' (default) or 'wav'. The 'wav' option is not encoded anywhere in the schema, so this adds real value. Minor gap: it doesn't clarify other format values or validation.

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 ('Extract the vocals from a song') and explicitly positions itself relative to a sibling by naming the equivalent call (process_audio with task_type='2stems'). An agent can distinguish this from process_audio and submit_separation without opening any 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?

Gives concrete use-case context (a cappella, karaoke, covers, vocal practice) and identifies the underlying alternative it shortcuts. It does not say when an agent should prefer process_audio or submit_separation directly (e.g., when more than two stems are needed), so the routing guidance is clear but not exhaustive.

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