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

With no annotations provided, the description carries the full disclosure burden and shoulders it well: it reveals that Android only dumps rendered nodes (scrolled-off elements are missing), that bounds are raw physical pixels usable directly with device_tap/device_swipe, and that `search` is a case-insensitive substring vs the exact `text` match. These are non-obvious behaviors an agent must know to avoid false-negative conclusions.

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?

Five front-loaded sentences with zero filler: core purpose first, then the highest-risk facts (coordinate semantics, rendered-nodes limitation), then filter options, and finally fallback routing. Every clause carries actionable information an agent needs before invoking.

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?

With no output schema, the description compensates by explaining what the dump contains (physical-pixel bounds) and its key limitation (only rendered nodes), plus what to do when an element is missing. Combined with 100% schema parameter coverage, nothing an agent needs to call it correctly and react to results 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 baseline is 3. The description adds incremental value by framing parameters as a task strategy: filtering by text/class, the compact description output format, and using `search` as the fast, deliberately looser presence check. It doesn't add new syntax beyond the schema, but it helps the agent choose which parameter fits the goal.

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 and resource: 'Get UI hierarchy XML of a device.' It goes beyond a terse purpose by anchoring the tool to Android (only rendered nodes are dumped) and by referencing the device_* sibling family, so an agent can distinguish it from ios_page_source or the session/web page-source tools without opening their schemas.

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?

Explicit when-to-use guidance: `search` is described as 'the fast way to check if a target is present,' and the description directly instructs the agent to switch to device_scroll_to_element, device_find_element/device_locators_for, or device_wait_for_element when the target is absent from the dump. It gives both positive usage conditions and explicit fallback routing to named alternatives.

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