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

Annotations cover only the safety profile (non-read-only, open-world, non-idempotent); the description adds substantial behavior beyond that: it consumes the account's plan and allowance, batch concurrency of two, asynchronous completion requiring polling, and that the full model needs Pro or a credit. That is exactly the kind of context the annotations cannot convey.

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: the core action and scope come first, then input format, then async lifecycle, then model options. Every clause carries operational information with no 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?

With no output schema, the description still tells the agent what happens after the call (immediate return for one song, queued batch otherwise) and how to retrieve results via get_split/get_batch. Nothing needed to invoke and complete the workflow 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?

Top-level parameters have 0% schema description coverage, and the description compensates fully: it defines each model enum value by the stems it produces (vocals/instrumental, drums/bass/other, guitar+piano) plus its plan requirement, and specifies the audio_url contract (public direct file link, Dropbox/Google Drive share links acceptable). This is meaning well beyond the raw 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?

States a specific verb (split), resource (songs into stems), scope (1 to 10), and execution context (connected StemConsole account, same as the website). It is clearly distinguishable from the single-file sibling split_audio by its explicit 1-10 batch range.

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 strong conditional guidance: one song runs immediately and returns its split, 2-10 are queued two at a time, and the agent is told to poll get_split or get_batch until status is done. It does not explicitly contrast against the split_audio sibling, so the routing is slightly incomplete.

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