Skip to main content
Glama
Sign In
Android Use

Android Use

by JackCaow
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

aua_long_press

Long-press once by selector or screen coordinates for 0.5–3 seconds, optionally wait for a condition and observe the result; inspect uncertain outcomes manually.

Instructions

Long press once by selector OR x/y display pixels for duration seconds (0.5..3). Supports wait_for and observe. Inspect uncertain results; no replay.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "aua_long_press"
  }
}

Input Schema

NameRequiredDescriptionDefault
xNo
yNo
visualNo
observeNonone
durationNo
selectorNo
wait_forNo
observation_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.6.0
    • addedInput schema / $defs / LocateArgs
      Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "description": {
+      "maxLength": 300,
+      "minLength": 1,
+      "title": "Description",
+      "type": "string"
+    },
+    "masks": {
+      "items": {
+        "$ref": "#/$defs/Region"
+      },
+      "maxItems": 8,
+      "title": "Masks",
+      "type": "array"
+    },
+    "min_confidence": {
+      "default": 0.5,
+      "maximum": 1,
+      "minimum": 0,
+      "title": "Min Confidence",
+      "type": "number"
+    },
+    "min_presence": {
+      "default": 0.7,
+      "maximum": 1,
+      "minimum": 0.5,
+      "title": "Min Presence",
+      "type": "number"
+    },
+    "package": {
+      "pattern": "^[a-zA-Z][a-zA-Z0-9_]*(\\.[a-zA-Z0-9_]+)+$",
+      "title": "Package",
+      "type": "string"
+    },
+    "region": {
+      "anyOf": [
+        {
+          "$ref": "#/$defs/Region"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null
+    },
+    "timeout_seconds": {
+      "default": 20,
+      "exclusiveMinimum": 0,
+      "maximum": 60,
+      "title": "Timeout Seconds",
+      "type": "number"
+    }
+  },
+  "required": [
+    "package",
+    "description"
+  ],
+  "title": "LocateArgs",
+  "type": "object"
+}
    • addedInput schema / $defs / Region
      Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "height": {
+      "exclusiveMinimum": 0,
+      "title": "Height",
+      "type": "integer"
+    },
+    "width": {
+      "exclusiveMinimum": 0,
+      "title": "Width",
+      "type": "integer"
+    },
+    "x": {
+      "minimum": 0,
+      "title": "X",
+      "type": "integer"
+    },
+    "y": {
+      "minimum": 0,
+      "title": "Y",
+      "type": "integer"
+    }
+  },
+  "required": [
+    "x",
+    "y",
+    "width",
+    "height"
+  ],
+  "title": "Region",
+  "type": "object"
+}
    • addedInput schema / properties / visual
      Added value: +{
+  "anyOf": [
+    {
+      "$ref": "#/$defs/LocateArgs"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}
  2. Addedv0.5.2

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, openWorldHint=true and idempotentHint=false; the description adds meaningful context beyond that: a bounded duration range, optional wait_for/observe post-behaviors, and the 'no replay' caution that explains the non-idempotent nature. It still does not describe what side effects a long press may trigger (context menus, drag initiation) or what happens on selector miss.

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

Conciseness5/5

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

Three compact sentences with the callable action front-loaded, the targeting alternatives next, and the caution last. No filler words and nothing repeated from structured fields verbatim.

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?

No output schema exists, so the description should explain the result shape, especially since 'observe' and 'observation_id' imply structured feedback; that relationship is unstated. For an 8-parameter, zero-coverage, non-idempotent action tool, the definition is minimally viable but incomplete.

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 0%, so the description must carry parameter meaning, and it only covers part of the 8 parameters: selector, x/y, duration (with its 0.5..3 range) and the existence of wait_for/observe. The 'visual' locate object, 'observation_id', and the observe enum values are never explained, leaving substantial gaps for a zero-coverage schema.

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+resource combination: 'Long press once' targeting either a selector or x/y display pixels. The verb itself distinguishes it from siblings aua_tap and aua_double_tap, and the two targeting modes are explicitly marked as alternatives with 'OR'.

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?

Provides implied usage through the verb and adds a caution ('Inspect uncertain results; no replay'), which tells the agent to verify after calling rather than chain a second identical call. It never explicitly says when to prefer it over aua_tap or aua_drag, nor what preconditions (e.g., element must be visible first) apply.

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

Deploy Server

Other Tools