Skip to main content
Glama

Check a notification

emu_check_notification

Waits for an app's notification to appear in the Android shade, then optionally taps it and verifies the app opens using a marker.

Instructions

Wait until a notification of the package whose title contains title is posted (dumpsys) and visible in the shade, optionally tap it and check the app opens (tap, opened_marker). Use it after the app scheduled a notification yourself (for example with emu_smoke notif_delay 0 and emu_clock forward). Needs this session's lease: NO_LEASE means emu_start first, BUSY means another session uses the emulator (wait or ask the person). Runs as a job: if the result is a job_id, call emu_job with it. Do not use mobile-mcp while it runs.

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": {
      "package": "<package>",
      "title": "<title>"
    },
    "name": "emu_check_notification"
  }
}

Input Schema

NameRequiredDescriptionDefault
avdNoAVD name (default "unity-test", or the EMU_AVD environment variable of the server).
tapNoTap the notification in the shade and check the app opens.
titleYesPlain substring of the notification title.
packageYesPackage name of the app that posts the notification.
since_msNoDevice epoch ms; only notifications posted at or after it count (default: device time when the check starts).
wait_secNoHow long this call waits for the job (default 50, max 600). If the job is still running, the call returns a job_id for emu_job.
timeout_secNoHow long to wait for the notification (default 240).
opened_markerNoText the app logs when opened from the notification (with tap).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations, the description discloses important session and execution behavior: it requires this session's lease, can fail with NO_LEASE or BUSY, runs as a job, and returns a job_id that should be passed to emu_job. It also warns not to use mobile-mcp while the check runs, which is valuable coordination context for an async tool.

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?

The description is front-loaded and every sentence contributes necessary operational context. It is somewhat dense as a single paragraph, and clearer separation of when-to-use versus lease/job mechanics would improve scanability, but there is little wasted wording.

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?

Given the async job model, lease requirements, and lack of an output schema, the description covers the critical failure modes and follow-up action for a returned job_id. The schema already documents the eight parameters, so the description does not need to restate return values.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is already 100%, so the parameters are well documented structurally. The description still adds useful relationships, especially that title is a substring match, package identifies the posting app, and tap is tied to opened_marker for verifying app launch.

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 description begins with a specific verb-and-resource statement: wait for a notification from a given package whose title contains a substring, confirm it is visible in the shade, and optionally tap it. It clearly distinguishes this verification workflow from sibling tools like emu_smoke and emu_clock by naming them as setup steps.

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

Usage Guidelines5/5

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

It explicitly says to use this after the app has scheduled a notification, gives a concrete setup example with emu_smoke and emu_clock, and specifies the lease prerequisite. It also explains the NO_LEASE and BUSY conditions and what to do in each case, which is unusually actionable guidance.

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