crosspad_kill

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

The description provides substantial behavioral detail beyond the annotations: the exact signal sequence (SIGTERM then SIGKILL after 3s), how the process is identified per-platform, and that it returns killed PIDs and port-answering status. The destructiveHint=true annotation is consistent with the kill semantics. The description adds process-identification mechanism and wait/signal timing, which creates real added value beyond the binary safe/unsafe flag.

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 dense but efficient — a single paragraph covering purpose, mechanism, timing, return values, and platform scope. Every sentence earns its place. Slightly long but justified given the multi-platform detection logic and signal sequence it must communicate.

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 destructive tool with an output schema present, the description is thorough: it explains the process identification strategy on Linux vs macOS/Windows, the graceful-then-forced termination sequence, what it returns (killed PIDs, port responsiveness), and the platform limitation. This is complete for a tool with a single enum-constrained parameter and full annotation coverage.

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 coverage is 100% — the single platform parameter is fully documented in the schema with enum and description. The description adds the [PC sim] and PC-only framing, reinforcing the enum constraint, but doesn't add meaning beyond what the schema's parameter description already provides. Baseline 3 is appropriate since the schema does the heavy lifting for this single simple parameter.

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 uses a specific verb ('Stops') with a clear resource (the running PC simulator). It details the exact termination mechanism (SIGTERM, SIGKILL after 3s, /proc/exe or pgrep match) and return values. It clearly distinguishes from sibling tools like crosspad_run (starts it) and lists the platform scope ('Currently PC-only').

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 clearly states the tool stops the running PC simulator, giving the operational context. While it doesn't explicitly name alternative tools or state when NOT to use it, the relationship to crosspad_run (which starts the sim) is implied by the purpose. The platform constraint is explicit, giving clear guidance on applicability.

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