Retrieve the Android device's current foreground activity, including package and activity name, to verify which screen is visible during debugging.
Get the currently visible activity on an Android device. Returns package and activity name.
| Name | Required | Description | Default |
|---|---|---|---|
| deviceId | No | Device Serial (Android). Defaults to connected/booted device. |
Changes observed during successful MCP inspections.
v0.34.0Input schema / allOfAdded value: +[
+ {
+ "not": {
+ "required": [
+ "expectedState"
+ ]
+ }
+ }
+]v0.31.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full disclosure burden. It does well on the return contract by naming the two pieces of information returned, but it says nothing about behavior on failure (no device attached, adb unavailable), whether it is a safe read-only call, or latency — meaningful gaps for a device-state query tool.
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?
Two short sentences with zero filler, and the core action is front-loaded ahead of the return-value detail. Nothing could be removed without losing information.
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 correctly covers the return value, and with one optional parameter at 100% coverage the schema handles input. The main remaining gap is error/ambiguity handling (multiple devices, no booted device), which would matter for an agent calling this blindly.
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?
The single parameter is fully documented in the schema ('Device Serial (Android). Defaults to connected/booted device.'), so baseline is 3. The description adds nothing about deviceId, such as how to resolve it via list_devices or what happens when multiple devices are connected.
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 verb and resource: retrieve the currently visible activity on an Android device, plus the exact return value (package and activity name). It is clearly distinct from siblings like get_ui_tree, capture_screenshot or get_screen_fingerprint in what it returns, though it never names those alternatives.
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?
Usage is only implicit: an agent can infer it is used to learn which app/activity is foreground. There is no explicit when-to-use statement, no exclusion telling the agent to prefer get_ui_tree or get_screen_fingerprint in other situations, and no prerequisites (e.g. device must be booted) called out.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.