preview_audio_task

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

Goes well beyond the readOnly/openWorld/destructive annotations by enumerating negatives: no backend polling, no media download, no generation, no spending, no configuration changes. It also discloses the interaction detail that playback starts only on user click, which the annotations cannot convey.

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?

Front-loaded with what is shown, then conditions, then constraints. Dense and mostly waste-free, though the final sentence about named original links for hosts without UI support is a host-rendering convention that sits slightly awkwardly in a tool description.

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?

No output schema exists, yet the description covers the return surface (separate versions, playback/seek controls, retry and original links) and the full safety profile for a read-only preview. An agent has everything needed to call it correctly once the task is complete.

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?

One parameter (task_handle) with 0% schema description coverage, so this dimension cannot lean on the schema. The description supplies context that the handle must reference an 'owned locally saved task', implying ownership and prior completion, but never states the handle format or where it comes from.

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 (Show) and resource (generated music/speech) plus the delivery mechanism (inline player) and the source constraint (owned locally saved task). It is immediately distinguishable from preview_image_task/preview_video_task and get_generation_task.

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?

"Call once when completed audio becomes available" gives an explicit trigger condition, and "Reads saved results only: no backend polling" steers the agent away from using this as a poller. It does not name the sibling that should do the waiting/polling, so it stops short of a 5.

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