Skip to main content
Glama

Two Minute Harvey Ball Matrix

create_harvey_matrix
Read-onlyIdempotent

Generate a slide-deck-quality Harvey ball matrix: options as rows scored against criteria as columns, every cell drawn in one style (Harvey balls 0–4 from empty to full, ticks 0/1, or 0–5 dots), with an optional highlighted 'Recommended' row, an optional notes column (appears when any row has notes) and a legend. Choose it to compare vendors, tools, plans or features side by side; use a timeline when the point is WHEN work happens, a process for ordered steps, a pyramid/funnel for a hierarchy or narrowing stages, and a hub and spoke, mind map or org chart for relationships. Limits: 2–12 rows, 1–8 criteria, row names up to 40 characters; scores outside the style's range are clamped and null leaves a cell blank. 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": {
      "rows": [
        {
          "name": "Salesforce",
          "scores": [
            1,
            3,
            4,
            3
          ]
        },
        {
          "name": "HubSpot",
          "scores": [
            3,
            4,
            3,
            3
          ],
          "highlight": true
        },
        {
          "name": "Pipedrive",
          "scores": [
            4,
            4,
            2,
            2
          ]
        }
      ],
      "style": "harvey",
      "title": "CRM vendor comparison",
      "legend": true,
      "criteria": [
        "Cost",
        "Ease of use",
        "Integrations",
        "Support"
      ]
    },
    "name": "create_harvey_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
rowsYesThe options being compared, top to bottom (2–12). Each has a name and one score per criterion, in the same order as `criteria`.
notesNoShow the Notes column on the right. true shows it even when no row has a note yet; false hides it (any row notes are kept but not drawn). When omitted, the column appears automatically as soon as any row has a note, so you can simply set rows[].notes.
styleNoCell style for the whole grid: "harvey" (Harvey balls, scores 0–4 from empty to full), "check" (a tick for 1, nothing for 0) or "dots" (0–5 filled dots out of five). Default "harvey".harvey
titleNoHeading shown top-left of the chart at 22px bold. Every chart has one title row; an empty string hides it.Comparison
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.
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 one-line legend under the grid explaining the scale. Default true.
paletteNoHex colours applied in order to items that have no colour of their own. Pass the user's brand colours here when they name them. Default: indigo, sky, emerald, amber, red, gray.
criteriaYesColumn headings, left to right: what each option is scored on, e.g. ["Cost", "Ease of use", "Integrations"]. 1–8 criteria, up to 40 characters each; long names wrap to two lines.

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

A4.6/5.0
Behavior5/5

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

Annotations only declare readOnly/idempotent/closed-world, so the description must carry the rest and does: clamping of out-of-range scores, null producing a blank cell, the notes column auto-appearing when any row has notes, character and count limits, and the builder Edit link for follow-up edits. It additionally discloses an output-delivery constraint (inline chat images usually can't be saved; the link renders the exact chart and is paste-able) that no annotation or schema conveys.

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 purpose, then alternatives, then limits, then output guidance — a sensible order with no filler sentences. It is dense and somewhat long, and the cell-style ranges are repeated from the schema, but each clause still carries actionable information.

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 10-parameter generation tool with no output schema, the description covers what is produced (PNG at 2x, legend, credit, computed height via schema), the constraints, and how to hand the result to the user. Nothing an agent needs in order to call it correctly or deliver the result is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents every parameter including style ranges, clamping, palette, width and credit. The description's parameter content (style ranges, notes-column behaviour, score clamping) largely restates those schema descriptions rather than adding new meaning, so the baseline 3 applies.

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 Harvey ball matrix") and immediately defines its structure: options as rows, criteria as columns, cells in one style. It also names sibling tools it is not (timeline, process, pyramid/funnel, hub and spoke), so an agent can separate it from the 19 other chart tools without opening a 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?

Explicit selection rule: "Choose it to compare vendors, tools, plans or features side by side", followed by four named alternatives with the condition that selects each (timeline = WHEN, process = ordered steps, pyramid/funnel = hierarchy, hub-spoke/mind map/org chart = relationships). It also states limits, says to infer missing details rather than ask, and instructs the agent to always surface the image link.

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