Skip to main content
Glama

Dispatch subworker

dispatch_subworker
Read-only

Spawn a focused child agent (subworker) for a narrowly-scoped task. Use this ONLY when (a) the work is parallelisable across siblings, (b) it benefits from a narrow tool list that keeps context small, or (c) you need a different model (e.g. planner_opus for Opus-level planning, registry_prober for cheap Haiku probes). Default execution stays single-loop in the parent agent; reach for subworkers when one of those three conditions clearly applies. Each subworker gets its own iteration budget (default 20) and its own narrow tool list keyed by worker_type. Workers do NOT see each other's transcripts unless share_context_with names a sibling explicitly.

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": {
      "worker_type": "<worker_type>",
      "task": "<task>"
    },
    "name": "dispatch_subworker"
  }
}

Input Schema

NameRequiredDescriptionDefault
taskYesConcise task brief for the subworker. Include the specific scope (cluster, namespace, resource names) and the expected output shape.
scopeNoOptional scope hints to bias the subworker's search: namespace, stack_name, draft_id.
worker_typeYesWhich subworker type to spawn. Each type has a pre-baked system prompt and narrow tool list: - cluster_explorer: read-only investigation - repo_explorer: read-only GitHub repository investigation (files, code search, CI runs) - manifest_author: draft/edit one manifest or Helm release - policy_auditor: RBAC / NetworkPolicy / OPA / Kyverno scan - incident_diagnoser: crashloop / pending / scheduling root cause - registry_prober: chart-existence and image-manifest probes (Haiku) - planner_opus: decompose a complex multi-stage turn into a todo list (Opus)
max_iterationsNoPer-subworker iteration budget (default 20, max 40).
requires_criticNoWhen true, the subworker's final output is run through the Critic regardless of the default gating rules.
share_context_withNoOptional list of sibling subworker_ids whose transcripts this subworker should be allowed to read. Default is isolation.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Beyond the readOnlyHint=true annotation, it discloses per-worker iteration budgets, per-type narrow tool lists keyed by worker_type, and that workers are transcript-isolated unless share_context_with names a sibling. It omits cost/latency implications and what happens if a subworker exhausts its iteration budget, which is material for a spawning 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?

Front-loaded with the core action and the when-to-use conditions before the operational details, with no filler sentences. The parenthetical examples are dense but earn their place by making the worker-type choice concrete.

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

Completeness4/5

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

For a complex dispatch tool with six parameters, a nested scope object, an enum and no output schema, the description covers the decision criteria, isolation semantics and iteration budgeting well. It does not describe what the caller receives back (transcript, summary, final answer) or how failures surface, which is the remaining gap given there is no output schema.

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 100%, so the baseline is 3, but the description adds real meaning: worker_type is explained in terms of model choice (Opus for planning, cheap Haiku for probes) and per-type capability, and share_context_with is framed as an isolation override rather than a plain id list. It adds little about scope or requires_critic beyond what the schema already says.

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 opens with a concrete verb+resource: "Spawn a focused child agent (subworker) for a narrowly-scoped task." It also differentiates from the default path by stating "Default execution stays single-loop in the parent agent," so an agent knows this is not the ordinary way to do work in this fleet of cluster/repo tools.

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 gives three explicit inclusion conditions — parallelisable work, need for a narrow tool list, or need for a different model — and implicitly excludes everything else by saying default execution stays single-loop. It also names concrete worker types (planner_opus, registry_prober) as examples of when the model-choice condition applies, which is actionable routing guidance.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.