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

Annotations already mark readOnlyHint=true, but the description adds non-obvious behavioral context: the job continues server-side and is saved to the gallery even if the client lost connection, and a taskId recovers a render already paid for. This goes beyond the structured annotations and gives the agent important persistence/recovery behavior without contradicting any annotation.

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 description is front-loaded with the core return value, then gives polling cadence, then the timeout recovery case. Each sentence contributes; the billing remark ('you already paid for') is marginally persuasive rather than purely informational, but the overall structure is efficient and focused.

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 a simple read-only polling tool with 2 parameters and no output schema, the description covers the return value, state progress, polling frequency, and a critical failure scenario. It doesn't enumerate possible state values, but that is a minor omission given the schema and annotations already provide a solid foundation.

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%: both taskId and kind are already described in the input schema, including the enum for kind. The description's mention that 'a taskId is enough' reinforces the parameter's role but does not add new semantic detail beyond what the schema provides, so the baseline of 3 is appropriate.

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: 'Returns the current state and, once finished, the output URL(s) for a job submitted with async:true.' It clearly differentiates from generation siblings by focusing on the async polling/recovery use case, so an agent understands exactly what this tool does and when it differs from tools like aetherwave_generate_video.

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 usage guidance is given: 'Poll this every 10-20s' and 'Use it whenever a generation call timed out too.' It also explains why (job keeps running server-side) and the recovery condition (taskId is enough), leaving no ambiguity about when to invoke this tool rather than resubmitting a generation.

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