human_activate

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

Annotations already flag destructiveHint=true and non-idempotent, and the description usefully confirms the risk model by demanding a fresh safe-area confirmation and re-observation afterwards. It says nothing about the human-like motion parameters (jitter, overshoot, duration, pause policy) or what failure looks like when the guard is violated.

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?

Three short sentences with the guard requirement front-loaded and the follow-up instruction last. Compact and ordered, though the terseness tips into cryptic in places.

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 10-parameter, nested-schema, destructive, no-output-schema tool, the description is far too thin. An agent gets the safety contract but not enough to reason about coordinate/target semantics or the mouse-path tuning knobs it must supply.

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 0% across 10 parameters including a nested pause_policy object with seven fields. The description only alludes to safe_area/safe_area_confirmed and leaves hwnd, x, y, jitter_px, duration_ms, overshoot_px and threshold_px entirely unexplained, so it fails to compensate for the coverage gap.

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?

"Guarded safe client click" conveys a click action constrained to a safe region, which is more specific than the bare name. However, "Distinct" gestures at a sibling (presumably human_mouse_click) without naming it, so an agent cannot tell precisely how this differs from the other click tools.

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?

Preconditions are stated: the caller must freshly confirm the safe area does not edit, navigate or submit, and must re-observe before further input. That is real guidance, but the description never says when to choose this over human_mouse_click or human_mouse_drag.

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