Skip to main content
Glama

Swarm presets (list, or show one to customise)

swarm_presets
Read-onlyIdempotent

List predefined swarm configurations or show one in full, with members, rubrics, and sources. Extend or replace built-ins using JSON files; broken files are flagged without consuming quota.

Instructions

List the predefined swarms preset_swarm can run, or show one in full. Spends no quota. Shows each preset's kind, members (role and backend), a jury's rubric, and where it comes from. Built-ins can be replaced or extended with JSON files in ~/.agent-intern/swarms/ (every project) or /.agent-intern/swarms/ (one project: its members run read-only and it cannot replace a built-in or user preset). Broken files are listed with the reason.

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": "swarm_presets"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoShow this preset in full, as the JSON to save and edit. Omit to list.
workspaceNoProject directory whose presets to include (default: server cwd).

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.32.1

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and idempotentHint, yet the description adds genuinely new behavior: it costs no quota, workspace-scoped presets run members read-only and cannot override built-ins or user presets, and broken files are surfaced with a reason. The precedence rules and the read-only constraint on project presets are exactly the kind of consequences an agent needs before relying on a listed preset.

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?

The primary capability and the no-quota guarantee are front-loaded, and the customisation details follow as context. The second sentence is dense with nested parentheticals and takes rereading, but every clause carries information an agent would otherwise have to discover by trial.

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 an output schema present, the description needn't document return shapes, and it still previews what listing shows (kind, members with role and backend, jury rubric, origin) and how failures appear (broken files with reasons). Listing, inspection, and customisation are all covered, which is everything this two-parameter read tool requires.

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; the description goes further by explaining that a named preset is returned as editable JSON to save and by describing which directories the workspace parameter reaches. Omitting name is explicitly stated to mean 'list', which reinforces the schema default rather than merely repeating it.

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 ('List the predefined swarms preset_swarm can run, or show one in full') and ties itself to the sibling that executes presets, so listing vs. executing is unambiguous. The dual mode (list vs. single-preset detail) is 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 Guidelines4/5

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

It's clear that a call with no name lists and a call with a name shows one in full, and that this tool is the read-side companion to preset_swarm. It also documents the customisation path (JSON files in ~/.agent-intern/swarms/ or <workspace>/.agent-intern/swarms/), but it never explicitly says when to prefer either directory or what to do after inspecting a preset.

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