Cancel async task

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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered structurally. The description adds real value beyond that by spelling out the exact task states in which the operation is a no-op rather than a cancellation. It stops short of saying what the caller receives or whether a failed cancel raises an error, which keeps it at 4.

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 sentences, zero filler, and the supported scope is front-loaded before the negative cases. Every clause (supported models, waiting-to-run condition, non-cancellable states) carries distinct information.

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 one-parameter mutation with no output schema, the description covers the essential decision inputs: which tasks are eligible and which are not. It is slightly incomplete on the outcome of a rejected cancellation (error vs. silent no-op), but annotations already flag the destructive/idempotent nature.

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?

There is a single parameter with 100% schema description coverage, so the schema already explains that `id` comes from `id`/`task_id` or a `poll_url`. The description adds no syntax, format, or value constraints for `id` beyond the schema, so the baseline 3 applies.

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 opens with a precise verb+resource ("Cancels a queued asynchronous task") and immediately bounds the scope to queued Seedance video tasks, distinguishing it from status/inspection siblings like get_task_status. An agent can tell exactly what this tool does and on what population without opening the schema.

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 an explicit precondition ("when cancellation is supported for the selected task") plus a positive list of supported models and an explicit negative list of states that cannot be cancelled (processing, completed, failed, expired, unsupported). This is when/when-not guidance with nothing left to inference.

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