Execute one validated Android UI action, synchronize the device state, and return semantic context or diff to verify the effect without blind retries.
Execute one validated UI/system action, synchronize, then return semantic context or diff in one round trip. Mutating actions are never blindly retried.
| Name | Required | Description | Default |
|---|---|---|---|
| wait | No | ||
| action | Yes | ||
| observe | No |
Changes observed during successful MCP inspections.
v0.8.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds meaningful behavioral context beyond the annotations: 'validated' indicates input checking, 'synchronize' reveals a built-in waiting step, and 'Mutating actions are never blindly retried' discloses retry safety behavior. This complements the existing destructiveHint and idempotentHint annotations without contradicting them.
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 tight sentences with no filler. The primary purpose is front-loaded, and the safety retry clause is concise. Every word earns its place.
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 tool is complex (nested wait/observe/action objects, multiple enums, no output schema) but the description only provides a high-level summary. It omits essential details like what action methods are available, how wait modes affect behavior, what 'context or diff' contains, and how the tool handles failures. The description is not sufficient for correct invocation without deep schema inspection or external knowledge.
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?
With 0% schema description coverage and three nested object parameters (action, wait, observe), the description should compensate by explaining what these parameters do. It does not—it only uses the words 'action' and 'synchronize' generically. No parameter names, defaults, enums, or method examples are mentioned, leaving the agent without crucial operational details.
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 identifies the tool as executing a UI/system action, synchronizing, and returning semantic context or diff in one round trip. It effectively distinguishes this composite tool from dedicated siblings like android_screen_diff, android_wait_idle, and android_ui_click. However, it doesn't explicitly mention the `action` parameter or the `observe`/`wait` options, so the exact mechanism is left to the schema.
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 explicit guidance is provided about when to use this tool versus the many sibling action, wait, and observe tools. The phrase 'one round trip' implies a combined workflow, but the description never states when a single action+observe call is preferable to separate calls or when it should be avoided. There are no exclusions or alternative tool references.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.