Stop a subagent

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

No annotations are provided, so the description carries the full burden. It discloses all key side effects: interrupts running turn, drops queued messages, marks stopped, and preserves the session. This is transparent about both destructive and reversible aspects, leaving nothing ambiguous.

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, no fluff. The core action is front-loaded ('Interrupt any running turn...') and the session-retention detail is appended naturally. Every word 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 single-parameter command with no output schema, the description is fully sufficient. It explains what happens, what persists, and how to resume. An agent can call it correctly with just this text and the schema.

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?

The input schema has 100% coverage: the only parameter 'name' is described as 'Subagent handle returned by spawn, e.g. coder-auth'. The description adds no extra parameter nuance, but none is needed; the baseline of 3 applies because the schema already handles it.

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 specific verb ('Interrupt'), the resource ('subagent'), and the concrete effects: drop queued messages, mark stopped, keep session. It clearly distinguishes from the sibling 'interrupt' by adding the drop-and-mark behavior, so an agent can tell them apart without reading either schema.

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?

It explains that the session is kept and can be resumed later, giving a clear reason to choose 'stop' over a more permanent or lighter alternative. It does not explicitly name 'interrupt' as a when-not-to-use case, but the behavioral distinction is implicit and sufficient for basic routing.

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