Skip to main content
Glama

Two Minute 2×2 Matrix

create_quadrant_matrix
Read-onlyIdempotent

Generate a slide-deck-quality 2×2 matrix, the classic consulting quadrant slide: two labelled axes (name plus low and high ends, rotated on the left) and four quadrants tinted in one accent colour. Two modes: "plot" places items as dots at x and y on 0–10 scales (or bubbles sized by size), with every label placed automatically so none overlap and quadrant names faint in the corners; "list" gives each quadrant a bold name and up to 6 bullets. Choose it to prioritise or position things on two dimensions: tasks, initiatives, features, products, brands, stakeholders or risks. Pick the preset that matches the request and let it supply the standard axes, quadrant names and mode: impactEffort for impact vs effort, quick wins or an action priority matrix; eisenhower for urgent vs important or a to-do list; bcg for a growth-share or product portfolio matrix (give revenue as size); ansoff for growth strategy (products × markets); powerInterest for a stakeholder map; perceptual for a perceptual or competitive positioning map (rename the axes to the user's attributes); riskLikelihood for a likelihood vs impact risk grid; none for any other 2×2 (name the axes and quadrants yourself; an omitted preset means none). Quadrants are keyed by position: topLeft, topRight, bottomLeft, bottomRight; with normal axes topRight is high x, high y. Use a Harvey ball matrix to score options against several criteria, create_five_forces for one industry's competitive forces, and create_swot for strengths, weaknesses, opportunities and threats. Infer realistic positions from context rather than asking. Limits: 30 items, names up to 40 characters (1–4 words read best), 6 bullets per quadrant. 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": {
      "items": [
        {
          "x": 2,
          "y": 8.5,
          "name": "Fix checkout errors"
        },
        {
          "x": 3.5,
          "y": 7,
          "name": "Self-serve onboarding"
        },
        {
          "x": 7.5,
          "y": 8,
          "name": "Enterprise SSO"
        },
        {
          "x": 9,
          "y": 6,
          "name": "Mobile app rebuild"
        },
        {
          "x": 3,
          "y": 2.5,
          "name": "Dark mode"
        },
        {
          "x": 7.5,
          "y": 2,
          "name": "Legacy report export"
        }
      ],
      "title": "Product initiatives: impact vs effort",
      "preset": "impactEffort"
    },
    "name": "create_quadrant_matrix"
  }
}

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
modeNo"list": four tinted quadrants, each with its name and bullets. "plot": items drawn as dots or bubbles at their x and y, with quadrant names faint in the corners. Omit to use the preset's mode (list for eisenhower and ansoff, plot for the rest).
itemsNoPlot mode only (kept but not drawn in list mode): 0–30 items, each a dot at its x and y on 0–10 scales, with its name beside it, e.g. { "name": "Self-serve onboarding", "x": 2.5, "y": 8 }. Labels are placed automatically so they never overlap. Give `size` to draw bubbles.
titleNoHeading shown top-left of the chart at 22px bold. Every chart has one title row; an empty string hides it.2×2 matrix
widthNoChart width in pixels (640–2400, default 1280, which suits a 16:9 slide). PNG output renders at 2x. Height follows from the width (plot mode) or the bullets (list mode).
xAxisNoThe horizontal axis along the bottom, e.g. { "label": "Effort", "low": "Low", "high": "High" }. Each field you omit comes from the preset; an empty string hides that text.
yAxisNoThe vertical axis up the left side, with rotated texts, e.g. { "label": "Impact", "low": "Low", "high": "High" }. Each field you omit comes from the preset; an empty string hides that text.
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).
presetNoSet it: the standard matrix to start from, or "none" (the default when omitted). Its axis labels, quadrant names and mode fill in anything the payload leaves out (your own values always win). eisenhower: urgency (urgent on the LEFT) × importance; Do first, Schedule, Delegate, Eliminate; list. impactEffort: effort × impact; Quick wins (top left), Major projects, Fill-ins, Thankless tasks; plot. bcg: relative market share (high on the LEFT) × market growth; Stars, Question marks, Cash cows, Dogs; plot. ansoff: products (existing, new) across × markets (existing at the TOP, new below); Market penetration, Product development, Market development, Diversification; list. powerInterest: interest × power; Keep satisfied, Manage closely, Monitor, Keep informed; plot. perceptual: price × quality; High value, Premium, Economy, Overpriced; plot. riskLikelihood: likelihood × impact; Plan contingency, Act now, Accept, Monitor; plot. none: plain Low/High axes and no quadrant names, plot (name the axes and quadrants yourself).none
paletteNoHex colours. The whole matrix uses the FIRST palette colour as its one accent, tinted in four strengths across the quadrants, so a brand colour as the first entry recolours the chart. Default: indigo, sky, emerald, amber, red, gray.
showGridNoPlot mode: light gridlines at every whole unit (1–9) behind the items. Default false (the midlines only).
quadrantsNoThe four quadrants by POSITION on the slide (after any axis reversal): topLeft, topRight, bottomLeft, bottomRight. With both axes in their normal direction, topRight is high x and high y, bottomLeft low x and low y. Each is { "name", "bullets", "color" }, all optional; a missing name comes from the preset. E.g. { "topLeft": { "name": "Quick wins", "bullets": ["Fix checkout bug"] } }.

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

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, but the description adds substantial operational context on top: hard limits (30 items, 40-character names, 6 bullets per quadrant), the instruction to infer realistic positions rather than interrogate the user, the existence of an Edit link in the builder, and the critical output-handling rule that the image link must always be given because inline chat images cannot be saved.

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?

It is a single long block, but it is front-loaded with the core definition and nearly every clause carries information an agent needs (modes, presets, keying, limits, output rule). The one weak spot is density: the preset enumeration and the closing output-handling instructions would scan faster as separate sentences or a short list.

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?

For a 12-parameter tool with nested quadrant objects and no output schema, the description covers everything an agent needs: which mode to pick, which preset maps to which real-world request, how quadrants are keyed, what the hard limits are, and how to hand the result to the user. Nothing material is left to inference.

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 100%, so the baseline is 3, and the description earns above that by explaining preset precedence ('your own values always win', an omitted preset means none) and by enumerating what each preset supplies — axis labels, quadrant names, mode and axis direction. It also clarifies the non-obvious quadrant-by-position keying and that topRight means high-x/high-y under normal axes, which is genuine interpretive value.

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?

Opens with a concrete verb+resource ('Generate a slide-deck-quality 2×2 matrix') and immediately specifies the visual anatomy: two labelled axes, four tinted quadrants, and the two output modes (plot vs list). It also explicitly distinguishes itself from named siblings — create_harvey_matrix for scoring against criteria, create_five_forces, and create_swot — so an agent can route correctly without opening another schema.

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 an explicit when-to-use trigger ('prioritise or position things on two dimensions: tasks, initiatives, features, products, brands, stakeholders or risks') and then maps request types to presets (impactEffort for quick wins, eisenhower for urgent/important, bcg for growth-share, ansoff, powerInterest, perceptual, riskLikelihood, none). It also states when NOT to use it by naming the sibling tools that cover adjacent diagram types.

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