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

Annotations already declare destructiveHint=true and openWorldHint=false, so the safety profile is covered. The description adds meaningful context beyond them: termination cascades to 'anything it started,' and only Shellway-spawned processes can be killed this way. It omits whether the kill is graceful vs SIGKILL (relevant given the 'force' name) and what a failure returns.

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 tight sentences with zero filler; the cascade behavior and the scope restriction are both front-loaded and immediately actionable.

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?

With no output schema and full annotation coverage, the description supplies the key behavioral facts an agent needs (cascade kill, Shellway-only scope). It is slightly thin on what success/failure looks like and whether termination is abrupt, which matters for a force-terminate mutation.

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?

Schema description coverage is 100%, with the pid parameter already explained as 'the pid returned by start_process' and device's optionality documented. The description adds nothing about parameter format or pairing, so baseline 3 applies.

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?

States a specific verb+resource ('Stop a process') and pins it to the sibling that creates such processes ('started with start_process'), which cleanly separates it from siblings like stop_search or interact_with_process. The scope note ('Only processes Shellway started') further narrows what this tool acts on.

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?

Gives a clear precondition for use — the process must originate from start_process — which tells the agent when this tool applies and implicitly when it does not (foreign/system processes). It does not name alternatives (e.g., interact_with_process for graceful control), so it falls short of explicit when-not guidance.

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