Get a compact semantic snapshot of the current Android screen with a content hash, including visible UI nodes and optional screenshot, to give the agent structured context for automating actions.
Preferred agent observation: compact semantic screen context with snapshot/hash. Screenshot is opt-in.
| Name | Required | Description | Default |
|---|---|---|---|
| maxNodes | No | ||
| treeMode | No | compact | |
| screenshot | No | ||
| includeInvisible | No |
Changes observed during successful MCP inspections.
v0.8.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already indicate read-only, non-destructive, and idempotent behavior. The description adds the opt-in nature of the screenshot, which is a behavioral detail not covered by the schema. However, it does not clarify potential side effects (e.g., whether it accesses accessibility services) or resource usage.
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 short and to the point, but the phrasing 'Preferred agent observation' and 'compact semantic screen context' is somewhat cryptic and could be more straightforward. It does not waste words, but the structure is not optimally clear for an agent.
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?
The tool lacks an output schema, and the description does not explain the return format or content beyond 'semantic screen context'. There is no mention of whether the result includes UI elements, coordinates, or just a summary. This leaves significant ambiguity about what the agent will receive.
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?
None of the four parameters (maxNodes, treeMode, screenshot, includeInvisible) are explained in the description. The schema provides defaults and constraints, but the description offers no semantic meaning for these options, leaving the agent to infer their purpose.
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 indicates the tool provides a compact semantic screen context, distinguishing it from raw UI tree tools like android_ui_tree. It also mentions the opt-in screenshot and snapshot/hash, which hints at its primary use for observation. However, 'preferred agent observation' is a bit vague and could be more explicit about the exact output.
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 guidance is given on when to use this tool versus alternatives such as android_screen_diff, android_ui_tree, or android_screenshot. The description implies it is for observation but does not specify conditions or scenarios where this tool is preferred over its siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.