desktop_stop

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

Goes well beyond the annotations by disclosing concrete side effects: running and queued actions are aborted, hung workers may be killed, and held keys/mouse buttons are force-released. The latching behavior and its consequence (user must click RESUME before further desktop control) is meaningful operational context, though it largely restates the schema field. Nothing contradicts the supplied hints.

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 densely packed sentence with the urgency marker front-loaded and the optional latching mentioned last. Nothing is redundant, though the multi-clause construction is slightly harder to parse than a short lead sentence plus detail.

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 zero-required-param, two-field control tool with annotations and no output schema, the description covers purpose, side effects, and the optional latch well enough to call it correctly. Only the relationship to overlapping siblings such as desktop_safety is left unspecified.

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%, so both `latch` and `reason` are already fully documented, including the RESUME consequence of latching. The description mentions optional latching but adds no meaning beyond the schema's own wording; 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 and resource: abort all running and queued desktop actions, plus kill hung workers and release held keys/mouse buttons. The scope is unmistakable and clearly the emergency-stop counterpart to the action tools, but the description never names a sibling (e.g., desktop_safety) to differentiate itself explicitly.

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 "URGENT: Immediately abort" framing and "if needed" clause imply the emergency context, so an agent can infer this is the panic-stop rather than an ordinary control call. However, it gives no explicit when-to-use versus desktop_safety or the desktop_actions family, and no when-not guidance or prerequisites.

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