Skip to main content
Glama

Wait for a job

emu_job
Read-onlyIdempotent

Wait for an emulator job to finish and return its result, or show status and latest report lines while it runs; omit the job ID to list this server's jobs.

Instructions

Wait for a job started by emu_start, emu_smoke, emu_check_notification or emu_release (job_id from their result) and return its result once it finished, or its status and latest report lines while it still runs (then call emu_job again). Without job_id it lists this server's jobs. JOB_UNKNOWN means the id is not known to this server (jobs do not survive a server restart): list the jobs or check emu_status.

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": "emu_job"
  }
}

Input Schema

NameRequiredDescriptionDefault
job_idNoThe job_id to wait for; omit to list the jobs.
wait_secNoHow long to wait for the job to finish (default 50, max 600).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the readOnly/idempotent annotations, it discloses the actual return behavior (final result vs. status plus latest report lines while running), the polling loop expectation, and the important durability constraint that jobs do not survive a server restart. It also names an error sentinel (JOB_UNKNOWN) and its remediation, which annotations cannot convey.

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 primary action and only three sentences, all of which carry information. It is somewhat dense, with stacked parentheticals ('(job_id from their result)', '(then call emu_job again)') that slow parsing, but no sentence is filler.

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?

With no output schema, the description still explains what comes back in both terminal and running states, plus error semantics and recovery. For a two-parameter, zero-required tool this covers everything an agent needs to call it and interpret the response.

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 are self-documented, so the baseline is 3. The description adds provenance for job_id ('from their result') and confirms the omit-to-list mode, but says nothing about wait_sec's default of 50 or its 600s cap, leaving that entirely to the schema.

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 (wait for / return result) and resource (job), and names exactly which sibling tools produce the job_id it consumes (emu_start, emu_smoke, emu_check_notification, emu_release), which cleanly separates it from those siblings. The dual listing behavior is also stated up front.

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?

Gives explicit when/when-not guidance: omit job_id to list jobs, call emu_job again if the job is still running, and on JOB_UNKNOWN list jobs or check emu_status. The alternatives are named and tied to triggering conditions rather than left to inference.

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