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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered; the description adds the valuable non-obvious facts that the call is free and that rerunning the original tool incurs a duplicate charge. It stops short of describing what the retrieved result contains, which matters given there is no output schema.

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?

Four short sentences, front-loaded with the purpose, then timing, then the failure mode to avoid, then the cost note. Every sentence adds decision-relevant information with no padding.

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 one parameter, no nested structures and no output schema, the description covers the polling workflow, the retry cadence and the cost trap well. A brief note on what the returned result looks like (e.g. an asset reference) would close the only remaining gap.

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% and the single 'job' parameter is already documented as coming from the 'Still generating' message, which the description repeats rather than extends. Baseline 3 is appropriate since the schema carries the parameter semantics.

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 ('Get the result of a generation') plus the precise condition that produces the need: the original tool said 'Still generating' and handed back a job. This clearly separates it from the generate_* siblings, which create assets rather than retrieve results.

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?

Explicit when-to-use ('Call it about a minute later'), explicit retry loop ('if it is still running, wait and call again'), and an explicit prohibition with reasoning ('Never re-run the original tool instead: that makes and charges a second one'). Nothing about routing is left to inference.

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