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

Beyond the readOnly/idempotent annotations, it discloses the hard per-call ceiling ('one call can never hold longer than 50 s'), the polling happens server-side, the still_running contract, and what a finished job returns (output, pre-signed artifact links, note). That is exactly the behavioral context annotations cannot convey for a long-poll tool.

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 purpose is front-loaded in the first clause, then the polling mechanics, then the retry rule and return shape. Dense but every sentence carries operational information; nothing is repeated from the schema verbatim.

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 carries the return-value burden and does so (output, pre-signed artifact links, note, still_running). Combined with the timeout ceiling and duration expectations, an agent has everything needed to drive the wait loop correctly.

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 real meaning: the 5–50 s timeout bound and the rationale that no single call can exceed 50 s, plus the hint to start from the submit reply's suggested_next_wait. It does not clarify the task_id + kind vs job_id precedence beyond what the schema already states.

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 gives a specific verb and resource ('Wait for an async doseedo job — a DAW conversion or a bounce — to finish') plus the mechanism (server-side polling). It stops short of naming the closest sibling, doseedo_check_task, so the boundary between a blocking wait and a status check is left for the agent to infer.

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 clearly states the repeat protocol: if still_running:true, call it again, and it sets expectations about typical durations (15 s–2 min for a conversion, bounce waits for the desktop render). It does not say when to prefer a one-shot status check or when to abandon the wait in favour of cancel_job.

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