Skip to main content
Glama

Preset swarm (jury / research / red team / council)

preset_swarm

Runs a predefined panel of model families (jury, research, red-team, council) in parallel, each in its own role on the same material, so repeated runs stay comparable.

Instructions

Best for getting something JUDGED, RESEARCHED or ATTACKED by several model families: runs a predefined panel (jury, research, red-team, council, or the user's own; swarm_presets lists them), each member in its own role on the same material, in parallel. The same panel every time, so two runs can be compared. Pass workspace=; without it the sub-agent sees no repo. Autonomous agents: trusted prompts only.

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": {
      "preset": "<preset>",
      "material": "<material>"
    },
    "name": "preset_swarm"
  }
}

Input Schema

NameRequiredDescriptionDefault
watchNoIf true, open the live "Agent Swarm" dashboard, one card per member, captioned with its role.
presetYesThe preset's name, e.g. "jury", "research", "red-team", "council", or one of the user's own.
materialYesThe text the panel works on, in full.
timeout_sNoPer-member timeout in seconds (default: the preset's own, 240-360s for the built-ins). opencode members get at least 300s.
workspaceNoDirectory the members run in, and whose .agent-intern/swarms/ presets are included (default: server cwd).
max_concurrencyNoMembers running at once (default 4).

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.32.1

TDQS

A4/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing parallel fan-out, panel determinism (repeatable comparisons), the workspace requirement ('without it the sub-agent sees no repo'), and an injection warning for autonomous agents. It does not describe failure behavior when individual members error out or the cost/latency profile of a multi-model fan-out.

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 'Best for...', then the mechanism, then the two practical cautions; every sentence carries information. The all-caps emphasis on JUDGED/RESEARCHED/ATTACKED and the parenthetical aside about swarm_presets make it slightly denser than it needs to be, but nothing is wasted.

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 six-parameter parallel orchestration tool with an output schema and full schema descriptions, the description supplies what structured fields cannot: the use case, the determinism guarantee, and the workspace pitfall. Remaining gaps (per-member failure handling, relative cost) are minor for selection purposes.

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 earns above that by explaining the consequence of omitting workspace (the sub-agent sees no repo) rather than merely restating the parameter. It also clarifies that preset must be one swarm_presets lists. Concurrency and timeout semantics are left entirely to the schema.

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 concrete verb and resource ('runs a predefined panel') and enumerates the built-in presets, plus the defining behavior: each member in its own role on the same material, in parallel. It routes to swarm_presets for the catalog, but does not contrast itself with agent_swarm, so an agent must infer how 'predefined' differs from the ad-hoc variant.

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?

'Best for getting something JUDGED, RESEARCHED or ATTACKED by several model families' gives a clear selection context, and 'the same panel every time, so two runs can be compared' explains the reason to prefer it over a one-off swarm. No explicit when-not-to-use or cost-based exclusion is given.

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