Skip to main content
Glama

Collect Adb Bugreport

collect_adb_bugreport

Collects a device-generated adb bugreport archive into a caller-selected output directory and digests the zip, enabling offline inspection of dumpstate, dumpsys, and logcat data.

Instructions

Collect one device-generated bugreport archive (adb bugreport) into a caller-selected output directory, digesting the zip. The archive contains the device's own dumpstate, dumpsys, and logcat report; collection can take minutes. Read-only with respect to configuration.

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": {
      "serial": "emulator-5554",
      "output_directory": "/tmp/rea-bugreports"
    },
    "name": "collect_adb_bugreport"
  }
}

Input Schema

NameRequiredDescriptionDefault
serialYesDevice serial exactly as `adb devices` reports it
output_directoryYesLocal directory for the bugreport archive; REA writes exactly one new zip into it

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, so the agent knows a non-idempotent write occurs; the description corroborates by explaining that an archive is written into the caller's directory and that config is only read. It adds real value beyond annotations with the wall-clock cost and the archive's contents (dumpstate, dumpsys, logcat), though 'digesting the zip' is left unexplained.

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, front-loaded with the action and destination, then the payoff and cost. Slight deduction for the vague 'digesting the zip' phrasing, whose effect on the returned artifact is never resolved.

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-parameter tool with no output schema, this covers cost, side effect (one new zip), and archive contents; the annotations supply the safety profile. The only real gap is what the call returns or where the produced file is identified afterwards.

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 100% and both parameters already document serial format and output-directory semantics, so the schema does the heavy lifting. The description only restates that the output directory is caller-selected, adding no format or constraint detail beyond structured fields.

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 specific verb and resource ('Collect one device-generated bugreport archive') plus the `adb bugreport` command it wraps and its destination. It is clearly distinct from log/pull siblings, though it doesn't name an alternative such as read_adb_logcat or pull_adb_file for narrower needs.

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?

Implied usage is discernible: use this when a full device bugreport archive is wanted, and the note that collection 'can take minutes' sets expectations for choosing it over faster targeted tools. There is no explicit when-not guidance or named alternative for agents who only need logs or a single file.

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