task_kill

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

With no annotations, the description carries the full burden. It discloses the SIGKILL signal, indicating a forceful, uncatchable kill, and notes its experimental purpose. It does not detail side effects or error behavior, but the SIGKILL mention provides meaningful behavioral context.

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 sentence, front-loaded with the action verb, and every clause adds value. It is compact and readable.

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 destructive tool, the description covers what is killed, how, and why. It lacks details about return values or handling of non-running tasks, but given the intentional simplicity and lack of output schema, it is reasonably complete.

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 schema only has jobDir with no description, and the description adds that the kill is 'by its lock pid', implying jobDir is the task directory containing that pid. This linkage is helpful but indirect; it could be more explicit about the relationship between jobDir and the lock pid.

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 uses a specific verb ('Kill'), identifies the resource ('running task'), and specifies the mechanism ('SIGKILL' via lock pid), clearly distinguishing it from sibling tools like task_wait or task_adopt.

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 phrase 'for crash/adoption experiments' gives clear context for when to use the tool, implying it's for fault injection rather than normal task termination. However, it does not explicitly mention when not to use it or name alternative tools.

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