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

With no annotations provided, the description carries the full burden. It discloses important behavior: bounds are physical pixel coordinates usable directly with device_tap/device_swipe, Android only dumps rendered nodes (so off-screen elements absent), and case-insensitive grep semantics. The only minor gap is not explicitly disclosing whether this is a read-only operation, though that's strongly implied.

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 information-dense and front-loaded with the primary purpose first. It's slightly longer than strictly necessary but every sentence adds distinct value (coordinate system, filtering, grep shortcut, off-screen caveat). The formatting with explicit tool name callouts is helpful for navigation.

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 tool with no output schema and no annotations, the description is thorough. It explains behavior (offscreen rendering limitation), coordinates, filtering semantics, output formats, and prioritizes alternative tools. A small gap: it doesn't describe the xml output structure detail or performance characteristics, but for a dump-inspection tool this is adequate.

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 documents all 5 parameters well. The description adds meaningful context beyond the schema: explains the coordinate system for bounds, distinguishes `search` (looser, case-insensitive grep) from `text` (exact match), and clarifies the `format` enum semantics. This goes beyond what the schema alone provides.

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 clearly states the tool retrieves UI hierarchy XML of a device, with specific scope (physical pixel bounds, filtering by text/class, compact description format). It differentiates from siblings like device_find_element, device_scroll_to_element, and device_wait_for_element by explicitly naming them as alternatives for specific use cases.

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?

Provides explicit guidance on when to use this tool (fast check for element presence via `search`), when NOT to rely on it (scrolled-off-screen elements not in dump), and names specific alternatives (device_scroll_to_element, device_find_element, device_wait_for_element). Also explains the distinction between `search` (loose grep) and `text` (exact match).

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