human_mouse_move

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

Beyond the annotations (destructive, non-idempotent, non-readonly), it discloses two genuinely important traits: the call blocks until completion ('waits for completion') and it has a side effect on other subsystems ('Cancels background reading first'). These are exactly the kind of facts an agent cannot infer from structured fields.

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?

Four short clauses, front-loaded with the verb and the primary behavioral fact, with zero filler. 'No auto focus' is terse to the point of being slightly cryptic, and the side-effect sentence would land better before the precondition, but the density is appropriate.

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 an 8-parameter tool with a 7-field nested tuning object and no output schema, the description covers behavior well but parameters almost not at all, leaving the entire pause/trajectory tuning surface opaque. An agent can call it with the three required fields but cannot reason about the optional ones.

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 8 parameters, and the description never mentions x, y, hwnd, jitter_px, duration_ms, overshoot_px, threshold_px, or any of the seven nested pause_policy fields. 'Bounded human-style path' vaguely gestures at the tuning knobs but gives an agent nothing actionable about units, defaults, or trade-offs.

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?

Specific verb and resource: 'Move ... the observed cursor through a bounded human-style path', which clearly separates it from human_mouse_click, human_mouse_drag, and human_scroll. It does not explicitly name those siblings as alternatives, but the operation is unambiguous.

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 cursor must already be inside the target client (use human_activate to enter)' gives an explicit precondition and routes to the right sibling when it is unmet. 'No auto focus' adds a clear negative constraint, though there is no guidance on when to prefer click/drag over a bare move, and no exclusions.

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