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

No annotations are provided, so the description carries full burden of behavioral disclosure. It does mention the tool operates in video coordinate space automatically, which is meaningful behavioral context. However, it doesn't disclose scroll duration/speed, whether the action is animated or instant, whether it's destructive/reversible, or any physical gesture nuances. For a scroll gesture tool with no annotation coverage, this is adequate but minimal.

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?

The description is two sentences long with zero filler. It front-loads the core purpose ('Scroll the screen in a direction on an Android device') and adds one valuable behavioral detail about coordinate space. Efficient and well-structured, though it could potentially mention the amount parameter semantics more explicitly.

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?

This is a simple gesture tool with 3 parameters (2 required), full schema coverage, and no output schema. The description covers the core purpose and the important coordinate-space behavior. However, it doesn't clarify the relationship to the closely-named sibling device_scroll_to_element, which is a notable gap since agents must choose between them. For a simple tool, this is adequate but could be more complete.

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 the schema already documents all three parameters (udid, amount, direction). The description adds value by explaining the video coordinate space context for the direction semantics, but doesn't elaborate on the 'amount' parameter beyond what the schema provides (fraction of screen). Baseline 3 is appropriate given full schema coverage.

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?

The description states a specific action (scroll the screen) on a resource (Android device) in a direction, which is clear. It distinguishes from sibling tools like device_swipe by noting 'No coordinate math needed', though it doesn't explicitly name the alternative tool (device_scroll_to_element) that handles scrolling to a specific element rather than a direction.

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 provides context about the video coordinate space automatically being handled, which is a helpful usage detail. However, it doesn't explicitly differentiate when to use this tool versus device_scroll_to_element or device_swipe, nor does it state when NOT to use it. Usage context is implied but not explicit.

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