Skip to main content
Glama

adb_test_step

Record a numbered test step by capturing a screenshot and logcat since the previous step into the session directory for verification and debugging.

Instructions

Capture a numbered test step: takes a screenshot and captures logcat since the last step. Saves both to the session directory.

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": {
      "description": "<description>"
    },
    "name": "adb_test_step"
  }
}

Input Schema

NameRequiredDescriptionDefault
descriptionYesDescription of what this step tests or verifies
captureLogcatNoCapture logcat since last step
captureScreenshotNoTake a screenshot for this step

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

A3.7/5.0
Behavior4/5

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

With no annotations, the description carries the behavioral disclosure burden and does so reasonably well. It reveals automatic step numbering, incremental logcat capture since the last step, and persistence to the session directory, though it omits session prerequisites and return behavior.

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 compact sentences front-load the operation and then state where artifacts are saved, with no filler. The wording is easy to scan and appropriately sized for the tool.

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?

For a simple three-parameter capture tool, the core behavior and storage destination are covered. However, the stateful workflow lacks an explicit active-session prerequisite, and with no output schema there is no indication of whether a step identifier or artifact paths are returned.

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?

All three parameters already have clear schema descriptions, so the 100% coverage establishes a baseline of 3. The description reinforces the screenshot and logcat roles but adds no further meaning for the required description parameter or the two capture toggles.

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?

The description clearly identifies the action and resource: capturing a test step consisting of a screenshot and logcat, then saving both. Its numbered, session-based framing provides some distinction from adb_screencap and adb_logcat, but it does not explicitly differentiate those siblings.

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?

It implies use while recording a multi-step test session, but never explains whether adb_test_session_start must be called first or when to prefer this over standalone screenshot and logcat tools. There are no explicit when-not or alternative-tool guidelines.

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