Skip to main content
Glama

phone_tap

Taps or long-presses an Android screen element by index, grid cell, pixel coordinates, or visible text, with OCR fallback for text not listed.

Instructions

Tap (or long-press) something on the phone. what to act on: element number from the last screen ("12"), grid cell ("C7"), pixel coordinates ("540,1200") or visible text ("Sign in"; text missing from the element list is found by OCR).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "target": "<target>"
    },
    "name": "phone_tap"
  }
}

Input Schema

NameRequiredDescriptionDefault
longNolong press
afterNoreturn the updated element list afterwards (default true)
settleNomax ms to wait for the screen to stop changing before reading it (default 2500)
targetYeswhat to act on: element number from the last screen ("12"), grid cell ("C7"), pixel coordinates ("540,1200") or visible text ("Sign in"; text missing from the element list is found by OCR)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the full behavioral burden, and it leaves key traits unstated: it never says this is a state-mutating interaction, whether the target app must be foregrounded, or what happens when the target is not found. It does disclose the 'last screen' state dependency and the OCR fallback, which is genuinely useful, and the schema covers settle/after timing, but for an unannotated interaction tool this is thin.

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?

Two sentences, action first, target formats second – well front-loaded with no filler. The only waste is that the target-format clause duplicates the `target` schema description word for word, which is redundant against structured data.

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

Completeness3/5

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

There is no output schema, so the description should convey what comes back, and it does not – return behavior is only inferable from the `after` parameter's schema note. For a 4-parameter interaction tool with no annotations, the description is adequate on targeting but silent on failure modes and result shape.

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

Parameters3/5

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

Schema description coverage is 100%, and the `target` parameter's schema text is verbatim identical to the description sentence, so the description adds no meaning beyond structured data. The `long`, `after`, and `settle` parameters are documented only in the schema. Baseline 3 applies when the schema does all the work.

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

Purpose4/5

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

A concrete verb plus resource ('Tap (or long-press) something on the phone') immediately separates it from phone_swipe, phone_type, and phone_key. The description goes further and enumerates the four accepted target formats, so an agent knows exactly what shape of input is valid. It stops short of naming a sibling explicitly, so it lands at 4 rather than 5.

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

Usage Guidelines3/5

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

Usage is implied rather than stated: 'element number from the last screen' reveals a state dependency (do a screen read first), and the OCR parenthetical hints at a fallback path when text isn't in the element list. There is no explicit when-to-use versus phone_swipe/phone_key/phone_type, and no when-not guidance or prerequisite statement.

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