Skip to main content
Glama

adb_iio_read

Read raw Linux IIO hardware values from Android devices to expose per-rail SoC power monitors and raw sensor channels, including data unavailable through the sensor HAL. Requires root.

Instructions

Read raw hardware data from the Linux IIO (Industrial I/O) subsystem. Discovers all IIO devices and reads their current values. On Tensor/Exynos devices, this exposes per-rail power monitors (ODPM) showing real-time power consumption per SoC subsystem (CPU clusters, GPU, display, memory, TPU, GPS, etc.) — data not available through the Android sensor HAL. On other devices, may expose raw accelerometer, gyroscope, magnetometer, or ADC channels. Root required.

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": "adb_iio_read"
  }
}

Input Schema

NameRequiredDescriptionDefault
deviceNoDevice serial
listOnlyNoIf true, list available IIO devices without reading values

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.1.6
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  2. Changed1 schema field changedv1.1.3
    • removedInput schema / additionalProperties
      Removed value: -false
  3. First observedv1.1.1

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the full load and does well: it discloses the root requirement, that it enumerates ALL IIO devices and reads all values (no filtering), and that results vary by SoC. It omits rate/cost implications of dumping every device and says nothing about the shape or volume of returned data.

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?

Front-loaded with the core action, then device-specific payoff, then the root prerequisite last. The parenthetical subsystem list (CPU clusters, GPU, display, memory, TPU, GPS) is slightly long but genuinely helps an agent judge relevance.

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 two-optional-parameter read tool with no annotations and no output schema, the description covers purpose, hardware variance, and the root prerequisite. The main residual gap is that with no output schema the agent gets no hint of the return structure for IIO device/value pairs.

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%, with both `device` and `listOnly` documented in the schema itself including the listOnly default and effect. The description adds no parameter-level detail beyond that, so the baseline 3 applies.

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 raw hardware data from the Linux IIO subsystem') and immediately scopes what that yields on Tensor/Exynos versus other hardware. The contrast with the Android sensor HAL makes it distinguishable from the similarly-purposed adb_sensor_read sibling.

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

Usage Guidelines4/5

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

Gives clear device-conditioned guidance: on Tensor/Exynos it is the way to get per-rail ODPM power data; elsewhere it may surface raw accel/gyro/mag/ADC channels. It stops short of an explicit 'use adb_sensor_read instead when you want HAL-normalized sensors', leaving the alternative routing to inference.

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