process_kill

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

The description adds significant behavioral detail beyond the annotations: it explains the default child-tree termination behavior ('by default, its discovered child tree') and the VM lock side effect ('VM remains locked by this session'). This goes well beyond the destructiveHint and readOnlyHint flags.

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 two sentences, front-loaded with the primary action, and efficiently communicates the key behavior (child tree) and a critical side effect (VM lock). Every word adds value, with no redundancy.

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 core purpose, the default child-tree handling, and the VM locking side effect. It does not mention error behavior or return values, but since no output schema exists, that information would be helpful. However, given the tool's relative simplicity (2 params, one required), the description is sufficiently complete for a highly destructive operation.

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?

With 0% schema description coverage, the description partially compensates by explaining the 'tree' parameter's default behavior ('by default, its discovered child tree'). It also implies that process_id identifies the target process. The schema already defines types and ranges, so the description adds meaningful context for the default tree behavior.

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 the action ('Terminate a process') and the resource (a process and its discovered child tree). This distinguishes it from sibling tools like shell_terminate, which deals with shell sessions, and process_list/process_wait which are non-destructive.

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 clear context: it terminates a process and by default its child tree, and explicitly notes that the VM remains locked and instructs to call vm_unlock when finished. While it does not explicitly mention alternatives ('use this instead of ...'), it gives practical usage guidance for a destructive operation.

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