Skip to main content
Glama

Two Minute SIPOC Diagram

create_sipoc
Read-onlyIdempotent

Generate a slide-deck-quality SIPOC diagram: five equal columns headed by big coloured letters, Suppliers, Inputs, Process, Outputs and Customers, with chevrons between them for the flow. Suppliers, inputs, outputs and customers are stacked cards; the process is 2–7 numbered step boxes joined by down arrows, with an optional process name and optional "Starts when" and "Ends when" boundaries. Choose it for Lean and Six Sigma project scoping (the Define phase of DMAIC), process-improvement kick-offs, quality and ISO documentation, and any slide that frames a process by who feeds it and who it serves; use a chevron process instead for a simple left-to-right sequence of phases with no inputs or outputs, an issue tree to break a problem into causes, and a timeline when dates matter. Limits: 1–7 steps (2 or more expected), up to 8 items in each of the other four columns; keep each item to a short phrase and start steps with a verb. 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": {
      "end": "Order is delivered and invoiced",
      "start": "Customer places an order",
      "steps": [
        "Receive order",
        "Check credit",
        "Pick and pack",
        "Ship",
        "Invoice"
      ],
      "title": "SIPOC: order fulfilment",
      "inputs": [
        "Purchase order",
        "Price list",
        "Stock"
      ],
      "outputs": [
        "Delivered order",
        "Invoice"
      ],
      "process": "Order to delivery",
      "customers": [
        "Customer",
        "Finance"
      ],
      "suppliers": [
        "Customer",
        "Sales team",
        "Warehouse"
      ]
    },
    "name": "create_sipoc"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNoOptional end boundary: the event that completes the process, shown below the steps as "Ends when …", e.g. "Payment is received". Omit for none.
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
startNoOptional start boundary: the trigger that begins the process, shown above the steps as "Starts when …", e.g. "Customer places an order". Omit for none.
stepsYesRequired: the high-level process steps, top to bottom (1–7, ideally 4–7; fewer than 2 renders with a warning, extras are dropped with a warning). Each is a step box joined to the next by a down arrow, e.g. ["Receive order", "Check credit", "Pick and pack", "Ship", "Invoice"]. Start each with a verb.
titleNoHeading shown top-left of the chart at 22px bold. Every chart has one title row; an empty string hides it.SIPOC
widthNoChart width in pixels (640–2400, default 1280, which suits a 16:9 slide). PNG output renders at 2x. Height is computed from the tallest column.
colorsNoOptional colour overrides per column, keyed by its letter, e.g. {"p": "#0f766e"}. Columns without one take the palette colours in order: S the first, I the second, P the third, O the fourth, C the fifth.
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).
inputsNoWhat the suppliers provide to the process (0–8), one card each, e.g. ["Purchase order", "Stock levels"].
outputsNoWhat the process produces (0–8), one card each, e.g. ["Shipped order", "Invoice"].
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.
processNoOptional name of the process, shown in bold at the top of the Process column, e.g. "Order to cash". Omit for none. Wraps to two lines, then truncates.
numberedNoNumber the process steps 1, 2, 3… in coloured circles. Default true; false shows plain step boxes.
customersNoWho receives the outputs (0–8), one card each, e.g. ["Customer", "Finance"]. Internal teams count as customers too.
suppliersNoWho provides the inputs (0–8; extras are dropped with a warning), one card each, e.g. ["Customer", "Sales team", "Warehouse"]. Short phrases; long ones wrap onto up to four 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 already declare readOnlyHint/idempotentHint/openWorldHint=false, so the safety profile is covered; the description goes well beyond that by disclosing capacity limits (1–7 steps, up to 8 items per other column), the rendering consequence of violating them ("fewer than 2 renders with a warning, extras are dropped"), the editability path via the builder Edit link, and the non-obvious fact that inline chat images usually cannot be saved. None of this is recoverable from the annotations.

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 artifact description before limits and alternatives, and nearly every clause carries information (constraints, exclusions, output-delivery instruction). It is a single dense paragraph with heavy clause stacking, though, which makes it harder to scan than a short bulleted structure would be; nothing is truly wasted.

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 15-parameter tool with nested objects and no output schema, the description still covers the things an agent needs: what gets built, hard limits, fallback routing to other diagram types, infer-don't-ask behavior, and how to hand the result to the user (always give the image link). No relevant gap remains.

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% and the description mostly restates what the schema already documents (step limits, short phrases, verb-first steps). It adds only marginal extra meaning, such as the note that missing details should be inferred rather than asked about, which is behavioral guidance more than parameter semantics. Baseline 3 is appropriate when the schema carries the parameter burden.

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?

Starts with a concrete verb and resource ("Generate a slide-deck-quality SIPOC diagram") and then specifies the artifact in detail: five equal columns, big coloured letters, chevrons, stacked cards, 2–7 numbered step boxes with down arrows. It also names the sibling shapes it is not (chevron process, issue tree, timeline), so an agent can distinguish it from the other create_* 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?

Gives explicit use contexts (Lean/Six Sigma scoping, DMAIC Define, process-improvement kick-offs, ISO documentation) and explicit when-not guidance routed to named alternatives: "use a chevron process instead for a simple left-to-right sequence… an issue tree to break a problem into causes, and a timeline when dates matter." That is exactly the when/when-not/alternative structure the dimension asks for.

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