Cancel a subagent invocation

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

Annotations already indicate destructive and idempotent behavior. The description adds useful nuance by explaining that the tool returns the final cancelled or already-terminal result, meaning it safely handles cases where the invocation is already done. This complements the annotations without contradicting them.

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 carry all necessary information, with the core action front-loaded and the alternative tool guidance placed second. No wasted words.

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 simple, one-parameter tool with an output schema and informative annotations, the description is fully sufficient. It explains what the tool does, when to use it, and how it differs from the sibling tool.

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 invocation_id parameter is well described as the ID returned by start_agent. The description adds minimal extra meaning beyond the schema, but the single-parameter context is straightforward.

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 states a clear, specific action: stop one invocation and return its cancelled or already-terminal result. It names the resource (agent invocation) and the effect, and distinguishes itself from wait_agent.

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?

Explicit guidance is provided: use this tool only when the Manager intends to stop active provider work, and use wait_agent to observe without stopping. This directly tells an agent when to choose this tool versus its sibling.

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