spatial_cancel_task

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is known. The description adds the side-effect note '[changes spatial-service]', which reinforces that this mutates service state, but it does not describe reversibility, consequences for the running task, or any additional behavioral risks beyond what the annotation already signals.

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 a single front-loaded sentence with no wasted words. The bracketed '[changes spatial-service]' is somewhat cryptic and redundant with the destructive annotation, but it does not meaningfully inflate the 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?

For a destructive two-parameter tool, this is minimally adequate: purpose, target state, and side-effect are present, and the confirm guardrail is documented in the schema. But the description does not explain what happens when a task is not cancellable, does not mention the require-confirm flow, and gives no sense of the response, leaving an agent to infer important operational details.

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 50%: only 'confirm' has a description, while 'id' is bare. The description does not document parameters directly, but 'Cancel a queued or running task' makes it inferable that 'id' identifies the task to cancel. The 'confirm' parameter is already explained in the schema, so the description adds no new parameter-level 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?

The description names a specific verb ('Cancel'), a specific resource ('a queued or running task'), and a clear scope. It is immediately distinguishable from siblings like run_task, rerun_task, and task_status because it is the only one that explicitly cancels an in-flight 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?

The phrase 'queued or running task' gives a clear condition for when the tool applies, implying it is not for completed tasks or task listing/status checks. However, it does not name alternatives or explicitly state when not to use this tool, so guidance is mostly implied rather than stated.

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