separate_ensemble

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

Annotations already declare non-readonly, non-idempotent, non-destructive, and closed-world behavior. The description adds that the tool queues a job and must be polled, which is meaningful context beyond annotations, but it does not mention file writes, overwrite protection, or ensemble compatibility constraints that an agent might need to know before invoking it.

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?

The description is two short sentences with no filler, and the purpose is front-loaded before the polling instruction. The word 'actual' is slightly awkward but does not meaningfully waste space.

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?

Because the input schema is richly documented and an output schema exists, the description does not need to explain return values. It does convey asynchronous queueing and polling, but for a complex ensemble tool it omits key context about compatible entries and algorithm selection, leaving it only minimally adequate.

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%, so the schema itself documents all eight parameters thoroughly. The description adds no parameter-level meaning for entries, algorithm, options, or output_dir, so the baseline of 3 applies.

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 uses the verbs 'Queue' and 'combine' with the resources 'model runs' and 'matching sources', but 'matching sources' is vague and it never explicitly says this is audio source separation. It also does not distinguish the tool from siblings such as separate_audio, start_separation, or separate_chain, so the agent must infer ensemble behavior from the name alone.

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?

'Poll get_job' gives a clear post-call step and implies asynchronous execution, which is useful. However, there is no explicit guidance on when to use this ensemble tool versus single-model separation siblings, and no when-not-to-use or alternative routing is provided.

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