Skip to main content
Glama
Sign In
maestro-plus

maestro-plus

by Fwmouomu
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

run_parallel

Run multiple Maestro flows concurrently across leased devices, distributing them round-robin to speed up mobile UI testing. Releases devices on exit, even on failure, and reports per-flow results.

Instructions

Run several Maestro flows in parallel across leased devices.

Flows are distributed round-robin over the leased devices, so N flows on M devices take roughly N/M rounds. Every device is leased for the duration and released on exit, including on failure, so a crashed run cannot strand a device.

Returns per-flow results plus wall-clock time, the sequential estimate, and the resulting speedup. A failure on one device never masks a pass on another: each result is reported separately.

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": {
      "flows": "<flows>"
    },
    "name": "run_parallel"
  }
}

Input Schema

NameRequiredDescriptionDefault
envNoMaestro environment variables, passed to every flow as -e KEY=VALUE.
flowsYesMaestro flow files to run. Paths resolve against the server working directory.
devicesNoPreferred device serials, tried first in order. Omit to use whatever the pool has free. A preferred device that is busy is skipped rather than fatal.
timeoutNoPer-flow timeout in seconds.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so well: round-robin scheduling, ~N/M round count, devices leased for the whole duration, guaranteed release on exit including failure (so a crash cannot strand a device), and per-device failure isolation. These are exactly the operational traits an agent needs before invoking a resource-leasing tool.

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?

Front-loaded with the core action and scope, then two short paragraphs covering scheduling and return/failure behavior. Every sentence carries information an agent would otherwise have to guess; nothing is restated.

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

Completeness5/5

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

There is no output schema, but the description compensates by describing the return payload (per-flow results, wall-clock time, sequential estimate, speedup) and the failure-reporting model. Combined with the 100%-covered input schema, an agent has everything needed to call and interpret this tool.

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 the schema already documents env, flows, devices, and timeout, including the busy-device-skipped rule. The description's mention of distribution and leasing adds context about how devices are used but not new per-parameter semantics. Baseline 3 is appropriate.

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?

The first sentence gives a specific verb ('Run'), resource ('Maestro flows'), and the distinguishing scope ('in parallel across leased devices'). That scope cleanly separates it from the sibling run_and_assert, which implies single-flow execution. No ambiguity about what the tool does.

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 parallel/multi-flow scenario is implied by 'Run several Maestro flows in parallel', and the device-pool behavior is explained, but there is no explicit when-to-use vs when-not guidance. It never states when to prefer run_and_assert or a single-flow path, nor does it note any prerequisites for leasing devices. Implied usage only.

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