start_separation

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

Annotations already declare non-readOnly, non-idempotent and closed-world, so safety is largely covered. The description adds the key trait annotations cannot express: execution is asynchronous and returns a queued job rather than results, with get_job as the completion path. It omits whether repeated identical calls create duplicate runs or how output_dir subdirectories are chosen.

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?

Two short sentences, zero filler. The async/queued outcome is front-loaded and the follow-up action is stated immediately after.

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 6-parameter tool with a large nested options object and an output schema present, the essentials an agent needs before calling are only partly covered: the async job model is clear, but model/profile selection and output-directory semantics are left entirely to the schema and sibling list_models.

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 100%, including detailed descriptions for audio_path, model, profile, output_dir and every nested option, so the schema carries parameter meaning fully. The description adds nothing about parameters beyond the schema baseline.

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: 'Start one separation and return a queued job.' The word 'one' hints at the single-run scope versus siblings like separate_batch, separate_ensemble and separate_chain, though those siblings are never named explicitly.

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 gives a downstream workflow ('Poll get_job for verified files'), which is useful routing. However, it never says when to pick this over separate_audio, separate_ensemble or separate_batch, nor what prerequisites (model catalog, profile) are needed.

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