kill

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

With no annotations, the description must disclose behavioral traits. It states 'kill' (a destructive action) and returns confirmation, but does not describe side effects (e.g., what happens if process doesn't exist), reversibility, or permission requirements.

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?

The description is extremely concise, using two short sentences plus a parameter list. Every sentence is necessary and front-loaded with the core purpose.

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 kill command with an output schema (confirmation), the description is minimally adequate. However, it lacks details on error handling, idempotency, and behavioral edge cases that would be expected given no annotations.

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 description adds meaning beyond the input schema: 'name' is clarified as 'Process name/ID from bg', and 'sandbox' includes a default value and context ('Named sandbox to use'). This compensates for the 0% schema coverage.

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 'Kill a background process' with a specific verb and resource. It distinguishes from sibling tools like 'bg' (which starts background processes) and 'destroy' (which destroys sandboxes), making its purpose unambiguous.

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?

No guidance is provided on when to use this tool versus alternatives (e.g., when to use 'kill' vs 'destroy' or 'bg'). The description does not mention prerequisites, exclusions, or context-specific advice.

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