Retrieve the Android UI hierarchy as a compact list of clickable or labeled elements with bounds and center coordinates to locate on-screen targets for automation.
Dump the UI hierarchy as a compact list of clickable/labelled elements with bounds and center coordinates
| Name | Required | Description | Default |
|---|---|---|---|
| serial | No | Device serial (optional; defaults to first ADB_SERIAL entry or the only connected device) |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It usefully describes the return shape (clickable/labelled elements with bounds and center coordinates), which is genuine behavioral information. However, it omits whether this is a read-only operation, any performance/pagination characteristics, or device-selection behavior.
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?
A single front-loaded sentence that leads with the verb and progressively narrows to the output format. No filler or redundancy.
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 no-annotation, no-output-schema tool, the description covers the essential return content (element names, bounds, center coordinates) that an agent needs to use the result. It leaves gaps on device-selection and read-only semantics, but is largely sufficient for a simple dump operation.
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?
One optional parameter (serial) with 100% schema description coverage, so the schema already documents the default-device fallback behavior. The description adds no parameter meaning beyond the schema. Baseline 3 is appropriate when the schema does the heavy lifting.
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 (Dump) and resource (UI hierarchy), then further specifies the output content: clickable/labelled elements with bounds and center coordinates. This clearly distinguishes it from screenshot (visual capture) and the interaction tools like tap_element, though no sibling is named explicitly.
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?
No when-to-use or when-not-to-use guidance is provided. The description never explains how this relates to alternatives like screenshot or tap_element, nor the workflow context (e.g., inspect-then-act). Usage is only inferable from the purpose statement.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.