process_kill

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds genuinely new context beyond them: the blast radius extends to the child process tree, and that tree behavior is Windows-specific. It still omits whether termination is graceful or forced and what happens on non-Windows hosts.

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?

A single sentence with the action front-loaded and zero filler. The Windows qualifier is placed where it is most relevant, immediately after the scope claim.

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 one-parameter destructive tool whose annotations fully declare the safety profile and which has no output schema, the description covers the essential what and blast radius. Minor gaps remain around failure modes (invalid or already-dead sessionId) and graceful vs forced termination.

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?

Only one parameter, and schema coverage is 0%, so the description must carry meaning but never mentions sessionId at all. The schema's uuid format plus strict pattern partially self-documents the expected value shape, but the description adds nothing about where to obtain a valid sessionId, so 3 is the ceiling.

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?

Names a specific verb (terminate) and resource (a persistent process session), which is enough to distinguish it from process_read, process_input, and process_start. It does not explicitly call out which sibling to use instead, so it stops short of full sibling differentiation.

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?

There is no explicit when-to-use guidance, no mention of prerequisites (e.g. a valid active sessionId), and no routing to alternatives such as process_list or process_input. The only usable cue is the implicit 'this ends the session', which the agent must infer.

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