Skip to main content
Glama

swarm

Coordinate multiple AI agents on separate tasks and synchronize progress through a shared message board; add, pin models to, title, monitor, or kill workers and manage channels.

Instructions

Manage the swarm of agents working on the shared message board. Actions: status, models, add, model, kill, title, channel.

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": {
      "action": "<action>"
    },
    "name": "swarm"
  }
}

Input Schema

NameRequiredDescriptionDefault
nNoOptional number of homogeneous copies to spawn (<name>-1..<name>-<n>).
opNoOperation for channel action.
allNoFor models: list all available models.
forkNoOptional roster name of an existing member to fork history from.
nameNoRoster name of the worker (short, lowercase, no spaces).
briefNoThe worker's assignment for add: what it owns and what done looks like.
modelNoModel identifier to pin this worker to. Leave unset to inherit.
tasksNoOptional per-worker slice targets for sharded groups (<name>-1..<name>-<k>).
titleNoA short descriptive title for the swarm.
topicNoTopic description for channel creation.
actionYesAction to perform: status, models, add, model, kill, title, or channel.
callerNoOptional caller roster name override when sharing a single MCP server.
channelNoTarget channel name for channel action.
channelsNoInitial channels to subscribe the new worker to.
workspaceNoWorkspace isolation mode: inherit, share (git worktree), or branch (clone).inherit

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

C2.5/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full behavioral burden and mostly drops it. It does not disclose that actions like kill destroy a worker, whether operations are reversible, what permissions or caller identity are required, or what any action returns. The only context added is the notion of a shared message board swarm.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short and front-loaded, but the second sentence is a pure restatement of the action enum that already exists in the schema, so it does not earn its place. There is no wasted prose beyond that, but also no structure mapping actions to their parameters.

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

Completeness2/5

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

For a seven-action, fifteen-parameter tool with no annotations and no output schema, the description explains none of the per-action parameter combinations (e.g. which fields matter for add versus channel versus model). The rich schema partially compensates, but an agent still has to infer action semantics entirely on its own.

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 description coverage is 100%, so all fifteen parameters are already documented in the schema, including the action enum, enums for op/workspace, and the n/tasks/fork fields. The description adds no meaning beyond that, but per the baseline for high coverage, a 3 is appropriate rather than lower.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a verb ("Manage") and a resource ("the swarm of agents working on the shared message board"), which is enough to know the general domain. But it is a multiplexed tool with seven actions, and the second sentence merely re-lists the action enum from the schema without saying what any action does. Nothing distinguishes it from siblings like swarm_wait or post_message.

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

Usage Guidelines2/5

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

There is no when-to-use guidance, no preconditions, and no routing to alternatives; an agent cannot tell from the text when to call swarm versus post_message or read_board. The action list implies capabilities but never states the situation each action is for.

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