Skip to main content
Glama

android_select_device

Destructive

Select the default Android phone for the current server session by unique ID, connection serial, or model, keeping the choice tied to its hardware ID across connection changes.

Instructions

Choose the default phone for this server session by unique id, exact connection serial or unique model from android_devices. Selection follows hardware id across connection changes and never switches silently if that phone goes offline.

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": {
      "selector": "<selector>"
    },
    "name": "android_select_device"
  }
}

Input Schema

NameRequiredDescriptionDefault
selectorYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.2.3

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, so the description is not obligated to restate mutability. It adds real context the annotations cannot: the selection is session-scoped, follows the hardware id across reconnects, and deliberately fails rather than silently re-targeting if the phone goes offline. It does not explain what a re-selection displaces for the previous default.

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?

Two sentences, no filler, with the core action and inputs front-loaded and the persistence/offline caveat following. Every clause contributes either input format or behavioral constraint.

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?

With one parameter, no output schema, and annotations covering the safety profile, the definition is nearly sufficient; it covers selector formats, scope, and the offline failure mode. The remaining gap is what the tool returns or how the caller confirms the new default, plus whether a connection is required first.

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 coverage is 0% for the single 'selector' string, so the description must carry the meaning, and it does enumerate three accepted forms: unique id, exact connection serial, or unique model. That is valuable, but it leaves ambiguity about precedence when a value could match more than one form and gives no format examples.

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 ("Choose") and a precise resource ("the default phone for this server session"), and points to android_devices as the source of valid selectors, which separates it from connect/discovery siblings. An agent can tell this is a session-level default selection, not a connection or enumeration operation.

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?

The phrase "from android_devices" implies the workflow (list first, then select), but there is no explicit when-to-use versus android_connect, nor any stated prerequisite such as the device needing to be connected. Usage is inferable rather than spelled out.

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