Skip to main content
Glama

Start Adb Activity

start_adb_activity
Destructive

Starts an Android activity on a specified device using adb am start -W, accepting action, optional data URI/component and typed extras, and retains the full wait report to verify success.

Instructions

Start an intent with am start -W: one action, optional data URI, optional explicit component, and up to 16 typed extras (string, boolean, int, long, float). A device-mutating tool; the full wait report determines success, with failed-attempt facts and raw output retained.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "android.intent.action.VIEW",
      "serial": "emulator-5554",
      "data_uri": "https://example.com/path"
    },
    "name": "start_adb_activity"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYesIntent action to start
extrasNoTyped intent extras (--es/--ez/--ei/--el/--ef)
serialYesDevice serial exactly as `adb devices` reports it
data_uriNoIntent data URI (-d)
componentNoExplicit component to start (-n)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=true, openWorldHint=true and idempotentHint=false, so the safety profile is covered. The description still adds real value by explaining the `-W` wait semantics and that success is judged from a full wait report while failed-attempt facts and raw output are retained — behavior an agent cannot get from the annotations.

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 tight sentences with the core operation front-loaded and the success-criteria caveat placed after it; nothing is redundant. The dense punctuation and adb shorthand make it slightly harder to parse than plain prose, but no sentence is wasted.

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

Completeness4/5

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

For a destructive, open-world mutation tool with no output schema, the description covers the underlying command, the parameter shape, and how success is determined including retained raw output. The only material omission is sibling differentiation, which the rest of the definition otherwise handles well.

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%, so every parameter is documented in the schema, including the `--es/--ez/--ei/--el/--ef` flag mappings and the 16-extra cap. The description restates those same facts rather than adding format, constraint or fallback detail beyond them, making the baseline 3 appropriate.

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?

States a concrete verb and resource ('Start an intent with `am start -W`') and enumerates the shape of the intent (action, optional data URI, optional component, typed extras), which is far more specific than the title. It does not, however, distinguish itself from the sibling `start_adb_app`, leaving the agent to infer that raw intent launching differs from package launching.

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

Usage Guidelines2/5

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

There is no when-to-use or when-not-to-use guidance, and no named alternative. The closest thing is the clause 'A device-mutating tool', which hints at caution but does not tell the agent when an intent start is preferable to `start_adb_app` or another sibling.

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