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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds valuable behavior beyond that: it blocks up to wait_seconds, requires repeated calls while running, and never starts or pays for anything — the cost/billing implication is the key extra signal.

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 tight sentences with the core action first, then the polling constraint, then the cost reassurance. No filler and nothing repeated from the schema or title.

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?

There is no output schema, and the description compensates by naming what comes back (viewer model, report, files), which is what an agent needs. It does not spell out what is returned when the wait expires without the job finishing, leaving one small gap for a polling tool.

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 baseline is 3, but the description adds meaning the schema does not: wait_seconds is a blocking wait, and a still-running result should trigger another call. That framing of wait_seconds as a polling interval is genuinely additive.

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 states a specific verb and resource: wait on a task_id and return its result, listing the result types (finished model in the 3D viewer, or report/files of print, Low Poly, rig, or craft jobs). It is clearly the polling/fetch tool, distinguishable from generation siblings, though it never explicitly contrasts itself with get_model or check_print.

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 concrete usage pattern: 'call again while it is still running', which tells the agent to poll in a loop. It also frames the tool as free and non-initiating, implying when it is safe to call, but it does not name alternatives or exclude any cases.

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