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

Annotations only declare the safety profile (readOnly/destructive/idempotent/openWorld). The description goes well beyond: it discloses the backend behavior (prefers HID touchscreen, falls back to injected MotionEvents), the densification semantics (waypoints sent AS GIVEN, not densified, so the polyline IS the gesture), and the coordinate space (physical pixels matching device_page_source bounds). These are exactly the traits annotations cannot express.

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?

Purpose and the device_swipe contrast are front-loaded, followed by point semantics, the densification caveat, backend behavior, and coordinate space. Each sentence carries distinct, non-redundant information; none restates the name, title, or annotations.

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 action tool with no output schema, the description supplies everything needed to invoke correctly: what the gesture means, point ordering and density requirements, coordinate space, and the execution backend with its fallback. Nothing an agent needs to call this successfully is missing.

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%, so the schema already documents udid, points, and durationMs, making the baseline 3. The description nonetheless adds meaning beyond it: the ordering convention (first = touch-down, last = lift), the minimum of 2 points, and the physical-pixel coordinate clarification that sharpens the schema's vaguer 'device tap-coord space'.

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 (Replay) and resource (freeform stroke as one continuous touch) and explicitly positions itself against the sibling device_swipe for gestures 'a straight device_swipe cannot express'. It also names its iOS counterpart ios_gesture_path, so an agent can distinguish it from every sibling without opening a schema.

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?

Gives explicit when-to-use criteria ('curves, arcs, signatures, unlock patterns, or any gesture a straight device_swipe cannot express') and names the alternative tool it supersedes. The selection condition between this and device_swipe is fully spelled out, leaving nothing to inference.

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