Captures the phone screen as a list of UI elements with ids, text, and tap coordinates so agents can inspect results before and after each action.
Read what is on the phone screen as a list of UI elements with ids, text, and tap coordinates. Call this first and after every action to see the result. Element ids are only valid until the next read_screen.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full behavioral burden, and it delivers the single most important non-obvious trait: 'Element ids are only valid until the next read_screen', which warns the agent that ids are ephemeral and must be re-read before acting. It does not cover failure modes (e.g., screen not ready, foreground app changes) or latency, which keeps it out of 5 territory.
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?
Three short sentences, each earning its place: what it returns, when to call it, and the id-staleness caveat. The most actionable information (when to call) is front-loaded right after the purpose statement, with no filler.
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 zero-parameter tool with no output schema, the description adequately conveys the return shape (elements with ids, text, coordinates) and the core workflow contract. It is slightly incomplete in not mentioning error/empty states or whether offscreen elements are included (requiring a scroll), which an agent would eventually need.
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 tool takes zero parameters, so there is nothing for the description to disambiguate; baseline is 4. The schema is empty and fully described, and no misleading parameter hints are given.
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 ('Read what is on the phone screen') and immediately characterizes the return shape as 'a list of UI elements with ids, text, and tap coordinates'. This implicitly and effectively distinguishes it from the sibling 'screenshot' (pixels) and 'browser_read' (web DOM) by naming the structured-element 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?
Gives explicit invocation guidance: 'Call this first and after every action to see the result.' That is a clear, prescriptive workflow rule an agent can follow directly. It stops short of a 5 because no alternative is named (e.g., when to prefer 'screenshot' or 'browser_read') and no when-not condition is stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.