Skip to main content
Glama

Two Minute RACI Matrix

create_raci
Read-onlyIdempotent

Generate a slide-deck-quality RACI matrix (responsibility assignment matrix): tasks or deliverables as rows, roles or teams as columns, and each cell a rounded letter chip, R Responsible, A Accountable, C Consulted or I Informed, with "A/R" for an owner who also does the work and model: "RASCI" adding S for Support. Rows can be grouped into phases with type: "section" rows; a legend explains the letters. With checks (default on), tasks without exactly one A or without an R get an amber note at the row end ("No A", "2 As", "No R") and every broken rule is returned in warnings; give every task exactly one A and at least one R unless the user's data says otherwise. Choose it for project roles and responsibilities, PMO governance, onboarding and handover plans, and any "who does what" slide; use a Harvey ball matrix instead to score options against criteria, an org chart for reporting lines, and a timeline when the point is when work happens. Limits: 1–10 roles and up to 30 rows (tasks plus sections); keep task names to a short verb phrase and roles to a job title. Infer missing details rather than asking; the user can adjust the chart in the builder through the Edit link. ALWAYS give the user the image link: inline chat images usually cannot be saved, but the link renders the exact chart on demand and can be pasted into a slide or Markdown.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "roles": [
        "Product owner",
        "Project manager",
        "Design lead",
        "Dev lead"
      ],
      "tasks": [
        {
          "name": "Discovery",
          "type": "section"
        },
        {
          "name": "Stakeholder interviews",
          "cells": [
            "A",
            "R",
            "C",
            "I"
          ]
        },
        {
          "name": "Build",
          "type": "section"
        },
        {
          "name": "Front-end build",
          "cells": [
            "I",
            "C",
            "C",
            "A/R"
          ]
        }
      ],
      "title": "Website relaunch RACI"
    },
    "name": "create_raci"
  }
}

Input Schema

NameRequiredDescriptionDefault
lookNoDrawing style, the same in every tool. "regular": clean lines and Inter (the default). "bold": heavier, slightly larger type and thicker lines, for slides read from a distance. "sketch": hand-drawn, with a handwriting font and pen lines that wobble a little, for early ideas and workshops. Use the one the user asks for; otherwise leave it out.regular
modelNo"RACI" (Responsible, Accountable, Consulted, Informed) or "RASCI", which adds S for Support. Sets the legend and the builder's click cycle; an S in a RACI chart is still drawn and added to the legend. Default "RACI".RACI
rolesYesColumn headings, left to right: the roles, teams or people, e.g. ["Project manager", "Dev lead", "Design", "Legal"]. 1–10 roles, up to 30 characters each; long names wrap onto up to three lines. Prefer roles over personal names.
tasksYesThe rows, top to bottom (1–30): tasks, deliverables or decisions, each with one cell per role. A row with "type": "section" is a full-width phase heading (e.g. "Discovery") that groups the tasks below it; it has no cells.
titleNoHeading shown top-left of the chart at 22px bold. Every chart has one title row; an empty string hides it.RACI matrix
widthNoChart width in pixels (640–2400, default 1280, which suits a 16:9 slide). PNG output renders at 2x. Height is computed from the content.
checksNoCheck the RACI rules: every task has exactly one A and at least one R (A/R counts as both), and every role is R or A on some task. Tasks that break a rule get an amber dot and a short note ("No A", "2 As", "No R") at the row end, and every broken rule is listed in `warnings`. Default true; set false to hide the notes.
creditNoShows a small "twominutetoolkit.com" credit under the chart, inside the card. Set false to leave it off (for example when the user asks for no branding).
legendNoShow a legend row under the matrix explaining each letter. Default true.
paletteNoHex colours: the first fills R chips, the second tints C chips, the third tints S chips (A is always dark and I light gray, so the letters stay distinct). Pass the user's brand colours here when they name them.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / look
      Added value: +{
      +  "default": "regular",
      +  "description": "Drawing style, the same in every tool. \"regular\": clean lines and Inter (the default). \"bold\": heavier, slightly larger type and thicker lines, for slides read from a distance. \"sketch\": hand-drawn, with a handwriting font and pen lines that wobble a little, for early ideas and workshops. Use the one the user asks for; otherwise leave it out.",
      +  "enum": [
      +    "regular",
      +    "bold",
      +    "sketch"
      +  ],
      +  "type": "string"
      +}
  2. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, openWorldHint false), but the description still adds real value: it discloses the validation behavior (amber notes plus a `warnings` array), the hard limits (1–10 roles, 30 rows), and the important operational caveat that inline chat images cannot be saved so the link must always be shared. The only gap is that the overall response payload beyond `warnings` and the link is not described.

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 deliverable, then alternatives, then limits, then the link instruction last in caps — a sensible order. It is dense as a single block and repeats limits that also live in the schema ('1–10 roles and up to 30 rows'), which costs a little.

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 10-parameter tool with no output schema, it covers the essentials: what is drawn, what gets validated, the size constraints, style defaults, and how to surface the result. It stops short of describing the returned object (link, warnings, any metadata), leaving the agent to infer the response shape.

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 baseline is 3; the description earns an extra point by explaining the semantics the schema only lists — that exactly one A and at least one R should be assigned per task, that `model: "RASCI"` extends the legend with S, and that `type: "section"` rows create phase groupings whose cells are ignored. It adds decision guidance ('unless the user's data says otherwise') rather than restating types.

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 — 'Generate a slide-deck-quality RACI matrix' — and immediately defines the structure (tasks as rows, roles as columns, letter chips). It explicitly distinguishes itself from the nearest alternatives (Harvey ball, org chart, timeline), so an agent can route between siblings without opening their schemas.

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?

Gives concrete positive triggers (project roles and responsibilities, PMO governance, onboarding and handover plans, 'who does what' slide) and explicit negative triggers with the alternatives to pick instead. It also supplies a fallback rule — 'Infer missing details rather than asking' — which removes ambiguity about how to proceed with incomplete input.

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.

Resources