Skip to main content
Glama

agy_council_create

Creates a multi-model council task with 2–4 selected AI participants to collaborate on a goal, supporting optional project linking, role assignment, and route configuration.

Instructions

Create a task with 2..4 selected participants including client gpt; defaults remain gpt/gemini/claude. Optional codex is an independent Codex CLI participant. routes maps each remote participant to {channel, model}; Claude requires Opus. Snapshots prevent implicit route/model changes. Unlinked tasks start with 1..8 attempts per remote (default 2, including initial judgment); explicitly link a lasting project with agy_project_link for on-demand collaboration without a lifetime round cap; agy_discussion_extend can explicitly add more without a model call. Prefer project for new projects: client first READS relevant files/docs, supplies stage/materials (source + observed contents)/success_criteria/constraints/unknowns, total <=3000 UTF-16 units. Collect all selected project understandings, reveal, then select roles with agy_council_assign_roles. Do not also preassign roles. Without project, legacy roles map remains supported. No model call or arbitrary project file reading.

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": {
      "goal": "<goal>"
    },
    "name": "agy_council_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
goalYes
factsNo
rolesNo
routesNo
projectNo
participantsNo
max_turns_per_modelNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.8.0
    • addedInput schema / properties / participants
      Added value: +{
      +  "anyOf": [
      +    {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Participants"
      +}
    • addedInput schema / properties / project
      Added value: +{
      +  "anyOf": [
      +    {
      +      "additionalProperties": {
      +        "type": "string"
      +      },
      +      "type": "object"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Project"
      +}
    • addedInput schema / properties / roles
      Added value: +{
      +  "anyOf": [
      +    {
      +      "additionalProperties": {
      +        "type": "string"
      +      },
      +      "type": "object"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Roles"
      +}
    • addedInput schema / properties / routes
      Added value: +{
      +  "anyOf": [
      +    {
      +      "additionalProperties": {
      +        "additionalProperties": {
      +          "type": "string"
      +        },
      +        "type": "object"
      +      },
      +      "type": "object"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Routes"
      +}
  2. First observedv0.5.2

TDQS

A4.4/5.0
Behavior4/5

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

With annotations declaring a non-read-only, non-destructive create operation, the description adds important behavior: snapshots prevent implicit route/model changes, Claude requires Opus, unlinked tasks have 1..8 attempts per remote, and creation makes no model call. It does not fully describe failure modes or return behavior, so it is strong but not exhaustive.

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?

The description front-loads the core create operation, but it is a dense run-on paragraph with many semicolon-separated concepts. Most sentences carry useful information, yet the lack of structure makes it harder to parse than necessary.

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 council-creation tool with no output schema, the description supplies substantial context: participant defaults, route requirements, project materials, attempt limits, and the required follow-on workflow. It still omits what the tool returns, such as the task identifier needed by sibling tools.

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 description coverage is 0%, so the description must carry parameter meaning. It meaningfully explains participants, routes, project contents and the 3000 UTF-16 unit limit, legacy roles, and the attempts/default behavior, though 'goal' and 'facts' remain mostly inferred from their names.

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 specific verb and resource: 'Create a task with 2..4 selected participants including client gpt.' It also distinguishes the tool from siblings by naming agy_project_link, agy_discussion_extend, and agy_council_assign_roles in the workflow.

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 explicitly states when to prefer project mode for new projects and how to sequence creation with reveal and agy_council_assign_roles. It also gives clear exclusions such as 'Do not also preassign roles' and alternatives like linking a lasting project.

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