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

Annotations only declare the generic safety profile (not read-only, not idempotent, not destructive). The description adds genuinely useful behavior beyond that: first call auto-sends CREATE then waits 250ms, and the input travels over a specific HID protocol channel. It leaves open whether device_uhid_destroy must later be called.

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 tight sentences, front-loaded with the action and then the behavioral caveat and parameter semantics. No filler, though the bitmask restatement is redundant with the schema.

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 stateful HID input tool with no output schema, the description covers the essential lifecycle fact (auto-CREATE + 250ms delay) and input encoding. The main remaining gap is the teardown story relative to device_uhid_destroy.

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 all six parameters (dx, dy, wheel, hWheel, buttons, udid) are already documented in the schema. The description's delta-range and button-bitmask notes duplicate that content rather than extending it, so the baseline of 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 (move/click) and resource (virtual mouse on an Android device), and the HID-mouse-id=1 channel distinguishes it from touch-based siblings like device_tap or device_swipe. It does not name those siblings explicitly, so differentiation relies on inference.

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 never states when to prefer hardware mouse input over touch gestures (device_tap, device_swipe) or over the raw device_uhid_input sibling. Usage is only implied by 'hardware mouse input via the device control protocol', with no exclusions or prerequisites for the UHID lifecycle.

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