mobilerun-mcp

Read Screen

read_screen

Captures the screen as a character grid with element IDs and actions, waiting for motion to stop. Enables automated taps, typing, and gestures on Android and iOS.

Instructions

Read the screen now (waits for it to stop moving first): the screen drawn as a character grid, each element a box with its som_id and label, then a table of what can be acted on: som (tap by this), in (som_id of the smallest box containing it), flg, label (only when it did not fit on the grid). Flags: * tappable, e text input (type_text, not tap), S scrollable, c toggle ON, o toggle OFF, l long-pressable, d disabled, - nothing declared (usually still tappable). N+k = som_id N plus k more elements with exactly those bounds; tap N. Header IDLE/BUSY: BUSY means it was still moving when the wait expired. Use perceive_screen instead for how something looks, when this ends with ESCALATE, or when what you need is missing.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`device`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 27, 2026

TDQS

A4.8/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does so richly: it discloses the blocking wait ('waits for it to stop moving first'), the BUSY/IDLE header semantics and what BUSY implies, the 'N+k' aggregation notation and the instruction to tap N, and the ESCALATE outcome. These are behavioral facts an agent could not infer from the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense but front-loaded: the core action and its blocking behavior come first, then the output contract, then the flag legend, then the routing note. The flag glossary and N+k note are long but each entry encodes a distinct actionable signal, so little is wasted; only mild compression is possible.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description defines the output format (character grid, element boxes with som_id/label, action table), decodes every flag, explains the header state, and gives the escalation/fallback route. An output schema exists, yet the description still adds the interpretive layer the schema cannot supply, making the definition complete for an agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Only one optional parameter exists (device, default null) and the description says nothing about it. However, with a single optional device selector and a rich, fully-specified output contract, the omission is minor; the description compensates for the 0% schema coverage by exhaustively defining the return structure the caller must interpret.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Read the screen now') and immediately scopes it with the wait-for-still behavior. It also names the sibling it is not (perceive_screen) and the reason to prefer that sibling, so an agent can route correctly without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states the alternative and the three conditions selecting it: 'Use perceive_screen instead for how something looks, when this ends with ESCALATE, or when what you need is missing.' This is textbook when-to-use/when-not guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server