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

Annotations already declare non-read-only, open-world, non-idempotent, non-destructive. The description adds the key trait annotations cannot express: the run survives client disconnection, and the intended polling loop via get_run. It does not say whether re-invoking creates duplicate runs (relevant given idempotentHint=false), which is the one obvious remaining gap.

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?

Three short sentences, front-loaded with the action and followed by the durability trait and the polling instruction. No filler, though the terseness is partly a symptom of the parameter gap rather than disciplined brevity.

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 an async start-job tool with no output schema, the description correctly conveys the lifecycle (start here, poll with get_run) so return values need not be documented. However, with four undocumented parameters at 0% coverage and a nested input object, it is not complete enough for an agent to invoke it confidently.

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?

All four parameters (input, model, modality, background) have 0% schema description coverage, and the description says nothing about any of them. The nested 'input' object and the modality enum are entirely unexplained, so an agent must guess at required content and accepted values.

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 a durable OneOver run') and names the sibling that continues the workflow (get_run). The 'OneOver' qualifier is jargon, and it does not distinguish itself from the other creation siblings (create_topup, build_create, run_app), but the core action is unambiguous.

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 implies when to use it by contrasting durability ('keeps going after the client disconnects') and gives a follow-up directive ('Poll with get_run'), which is genuine routing guidance. It does not say when a non-durable or synchronous alternative such as chat or run_app would be the better choice.

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