Skip to main content
Glama
Sign In
Task Queue MCP

Task Queue MCP

by devops-riku
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Start a task

start_task

Starts a queued task or corrects its start time, requiring an estimate when none exists. Read a reassigned task's comments first.

Instructions

Starts a queued task (or corrects the start time of one already started). A task without an estimate needs estimate_minutes. A reassigned task: read its comments (get_task) first.

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": {
      "task": "<task>"
    },
    "name": "start_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
taskYesThe task: its number, e.g. TASK-000123, or its id.
started_atNoWhen work started, ISO 8601 with a UTC offset, e.g. 2026-11-13T09:30:00+08:00. Default: now.
estimate_minutesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.2

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare this is a non-read-only but non-destructive mutation with open-world side effects. The description adds the useful correction/idempotency behavior and a conditional dependency on task comments, but says nothing about side effects on status, notifications, or failure modes when the task is already started.

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?

Three short sentences, front-loaded with the primary action, with no filler. The final sentence is terse enough ("A reassigned task: read its comments (get_task) first") that the agent must infer whether get_task is the comment-reading 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 three-parameter mutation with no output schema, the description covers the input preconditions but not the outcome: it does not say what state the task ends up in, what errors can occur (e.g., starting an already-started task without started_at), or what is 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?

Schema coverage is 67%; task and started_at are already documented in the schema. The description does add real meaning for estimate_minutes, which has no schema description, by making it conditionally required when the task lacks an estimate, but adds nothing about the started_at format or the accepted task identifier forms.

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+resource ("Starts a queued task") and adds a secondary mode (correcting the start time of an already-started task). It does not explicitly distinguish itself from siblings like resume_task or pause_task, leaving the boundary up to inference.

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

Usage Guidelines4/5

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

Gives two concrete preconditions: supply estimate_minutes when the task has no estimate, and call get_task to read comments first for a reassigned task. It names a sibling tool explicitly, though it never states when not to use this tool versus resume_task.

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