Cancel TraeCN Task

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

Annotations already declare destructiveHint=true, and the description adds value beyond that by specifying what is and is not destroyed: the gateway records the cancellation and 'results already produced remain in task history.' It also discloses the return payload (task identity and post-cancellation status). This contextualizes the destructive nature usefully and does not contradict the annotations.

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?

Three sentences, front-loaded with the primary purpose before the behavioral details. Each sentence earns its place — scope, behavior/side-effects, and return value. Slightly more verbose than strictly necessary to state the operation, but no wasted content.

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 single-parameter cancellation tool with an output schema and provided annotations, the description is largely complete. It covers side effects (what stops, what persists) and the return shape. The only minor gap is the unstated relationship to traecn_stop_generation, which an agent might confuse it with given the sibling set.

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 100%, and the schema already documents taskId as the 'Stable task identifier returned by traecn_send_message.' The description only references 'by ID' and adds no new syntax, format, or provenance detail beyond the schema. At 100% coverage, the schema carries the burden, so a baseline 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?

States a specific verb ('cancel') and precise resource ('one gateway-tracked task by ID'). The mechanism of action — gateway stops shepherding at the next control point — further specifies the operation. This clearly separates it from siblings like traecn_get_task (read) and traecn_send_message (create).

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 description conveys the effect (stops shepherding, retains results) and scope (single task by ID), which implies when it applies. However, it does not explicitly distinguish itself from the likely-overlapping sibling traecn_stop_generation, nor state any exclusions such as 'for a running generation use stop_generation instead.' The context is clear but the contrast with alternatives 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.