kill_process

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

With no annotations, the description carries the transparency burden and does offer meaningful behavior details: TERM is graceful, KILL is force, HUP is reload, and host_name falls back to a configured default. However, it does not warn about the destructive nature of KILL, permission requirements, or what the returned result actually contains.

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 compact and well-structured with Args and Returns sections. There is no filler content, though a few line breaks and the 'Args:' scaffold add minor structural noise.

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?

The description covers the tool's purpose, all parameters, and the return value. Given the moderate complexity and presence of an output schema, this is sufficient, though explicit use-case guidance and safety warnings would push it higher.

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 Args section fully explains all three parameters, including the meaning of pid, the signal values with defaults, and the host_name source from SSH_HOSTS with default-host fallback. This fully compensates for the 0% schema description 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 opens with a clear verb and object: 'Send a signal to a process by PID.' This is specific and distinguishes the tool from sibling process tools like list_processes and find_process, which do not send signals.

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 description provides no explicit guidance on when to use kill_process versus alternatives such as manage_service or execute_command. It explains signal semantics and host defaults but does not state when-not-to-use or mention alternative tools.

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