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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower. The description adds real value beyond them: the concrete status enum (queued/processing/completed/failed) and the fact that the download URL is time-limited.

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 that are front-loaded with the operation and its origin, followed by the return behavior. Every clause earns its place.

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 correctly carries the return-value burden by enumerating possible statuses and the download URL. It is nearly complete; minor gaps remain around failure-mode handling and how long the URL stays valid.

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 0%, so the description must compensate for the single `generation_uid` parameter. It only indirectly conveys that the uid originates from a prior `generate_3d_model` call; it gives no format, length, or validation detail, so it adds partial but not full meaning.

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 (Poll) and resource (a PrintPal AI generation) and explicitly ties itself to the sibling tool that creates the job (`generate_3d_model`). It also names the return artifact (status + download URL), so an agent can distinguish it from generate_3d_model and get_3d_model immediately.

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 frames when to use it: polling a generation that was started with `generate_3d_model` in API-key mode. It stops short of naming exclusions or an alternative retrieval tool (e.g., get_3d_model), so the routing is clear but not fully disambiguated.

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