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

Beyond the destructiveHint/readOnly annotations, the description discloses three concrete behaviors: submissions are blocked, existing work remains reviewable, and the unused balance is refunded automatically. It does not explicitly say whether cancellation is final, but the destructiveHint annotation already covers that safety signal.

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?

One front-loaded 13-word sentence conveys the action and the two most important outcomes, with no filler. Every clause earns its place.

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 financial action, the description covers the core lifecycle—stop, review, refund—so an agent knows what invoking it will do. The main omissions are parameter-level guidance and explicit finality, but the schema plus idempotent/destructive annotations help fill the 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?

With only 33% schema description coverage, the description needed to explain task_id, request_id, and agent_key, but it mentions no parameters. The schema provides patterns rather than semantics, so the role of request_id in this idempotent cancellation is left undocumented.

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 the exact operation on a funded task—stopping new submissions and refunding unused balance—rather than restating the title. The refund clause separates it from sibling pause/cancel tools by making the cancellation outcome concrete.

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 use case is implicit: call this when a funded task should be canceled and its remaining funds returned, and the refund wording suggests it is not a temporary pause. However, it never explicitly says when to prefer this over speedbot_exchange_funded_task_pause or speedbot_exchange_cancel, so routing guidance 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.