bernstein_cancel

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

Describes cascading behavior via parent_task_id, endpoint, cancellable statuses, handling of terminal tasks and unknown IDs, and return format. No annotations provided, so description fully covers behavioral traits.

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?

Well-structured with short summary, followed by details and argument documentation. Front-loaded with purpose. Slightly long but each part is informative.

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?

Given that output schema exists (not shown), description still explains return format and error cases. Covers all necessary context for ability to use correctly.

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?

Adds meaning beyond schema: task_id is the root task whose descendants are cancelled, reason is optional. Schema only specifies type and constraints, so description provides valuable context.

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 clearly states 'Cancel one task and its subtask tree; the orchestrator keeps running.' It uses a specific verb (cancel) and resource (task with subtask tree), and distinguishes itself from sibling like bernstein_shutdown_orchestrator.

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?

Explicitly states when to use (cancel a task and its subtree), when not to (for stopping orchestrator, use bernstein_shutdown_orchestrator), and covers cancellable statuses and handling of terminal/unknown task IDs.

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