Skip to main content
Glama

Post a task to the dispatch hub

hub_post

Queues a self-contained task for hub workers to run in the background. Use it to offload code, text, or review jobs, then wake via hub_wait when the result needs attention.

Instructions

Queue a task for the dispatch hub's workers (ZCode / CLI agents on the hub host, manual workers on remote machines). Returns once the task is queued; a daemon assigns and runs it, and hub_wait wakes you when it needs attention. The task body must be self-contained (the worker cannot see this conversation). Code tasks need repo (absolute path on the hub host) and base (commit sha); the worker's changes come back as a patch that is replayed and checked by the hub's acceptance step.

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": {
      "title": "<title>",
      "task": "<task>"
    },
    "name": "hub_post"
  }
}

Input Schema

NameRequiredDescriptionDefault
baseNoCommit sha to build on. Default: the repo's HEAD when the daemon prepares the task.
kindNoDefault code.
repoNoAbsolute path of the git repo on the hub host (code tasks).
taskYesMarkdown instructions for the worker (task.md).
tierNoDefault mid.
titleYes
acceptNoCommand run with bash -o pipefail in a fresh checkout + the patch (no node_modules: install first); non-zero exit rejects.
reviewNoHave a second, different-vendor agent review the patch before acceptance.
timeoutMinNoDefault 45.
avoidVendorsNo
preferWorkersNo
acceptTimeoutMinNoAccept command time limit. Default 30.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A4.6/5.0
Behavior5/5

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

Goes well past the annotations: it discloses the async contract ('returns once the task is queued; a daemon assigns and runs it'), the isolation constraint on the task body, and the acceptance pipeline for code tasks (patch replayed in a fresh checkout, non-zero exit rejects). These are the operational facts an agent needs for a non-idempotent, open-world dispatch.

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?

Four sentences, front-loaded with purpose and the returns/async behavior before the caller obligations. Dense but nearly every clause carries new information; the worker list in the first parenthesis is the only slightly heavy aside.

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?

For a 12-parameter, non-idempotent dispatch tool with no output schema, it covers the essentials: what happens after the call, who runs the work, what the worker can and cannot see, and how code output is validated. The one omission — that a task identifier is presumably returned for use with hub_wait/hub_show — is minor and largely implied by the named follow-up tool.

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 75%, so the baseline is 3, and the description earns above that by adding meaning: repo must be an absolute path on the hub host, base is a commit sha the work builds on, and code changes return as a patch. It does not explain tier, timeoutMin, preferWorkers, or avoidVendors, leaving those to the schema defaults.

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 and resource ('Queue a task for the dispatch hub's workers') and immediately names the worker population (ZCode/CLI agents on the hub host vs. manual workers on remote machines). The async handoff to hub_wait is named, so an agent can distinguish this from the polling/inspection siblings without opening a schema.

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?

Clear context for use: fire-and-forget queuing where the caller is told hub_wait will wake it, plus the constraint that the task body must be self-contained because the worker cannot see the conversation. It stops short of exclusions — nothing says when to prefer this over the swarm_*/zcode_* run siblings that also dispatch work.

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