Skip to main content
Glama

Two Minute Fishbone Diagram

create_fishbone
Read-onlyIdempotent

Generate a slide-deck-quality fishbone diagram (Ishikawa or cause-and-effect diagram) for root-cause analysis: a horizontal spine ending in a head box that holds the problem, with 1–8 category bones angled off it, alternating above and below, each named in a coloured pill and carrying up to 6 causes, and each cause up to 3 sub-causes. Standard category sets fill in unnamed categories: 6M for manufacturing (People, Machine, Method, Material, Measurement, Environment), 8P for services and 4S for the service industry. Choose it for quality, Lean and Six Sigma (DMAIC Analyze) work, healthcare quality improvement, incident reviews and any "why does this keep happening" slide; use an issue tree for a MECE logic or KPI breakdown, a mind map for an open brainstorm, a SIPOC to scope a process, and the lab fishbone (create_lab_fishbone) for lab value skeletons such as BMP or CBC, which is a different thing. Infer 4–6 categories and 2–4 causes each from the problem rather than asking. Limits: 1–8 categories, 6 causes per category of about 2–7 words, 3 sub-causes per cause. 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": {
      "title": "Root cause analysis: Ward 4B",
      "problem": "Late medication administration",
      "categories": [
        {
          "name": "People",
          "causes": [
            {
              "text": "Agency nurses unfamiliar with ward routine"
            },
            {
              "text": "High patient-to-nurse ratio on nights"
            }
          ]
        },
        {
          "name": "Methods",
          "causes": [
            {
              "sub": [
                "Clashes with handover"
              ],
              "text": "All rounds timed for 08:00"
            }
          ]
        },
        {
          "name": "Equipment",
          "causes": [
            {
              "text": "One medication cart for 28 beds"
            }
          ]
        },
        {
          "name": "Materials",
          "causes": [
            {
              "text": "Pharmacy delivers after the morning round"
            }
          ]
        }
      ]
    },
    "name": "create_fishbone"
  }
}

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
titleNoHeading shown top-left of the chart at 22px bold. Every chart has one title row; an empty string hides it.Root cause analysis
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: bones grow as long as their causes need.
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).
presetNoStandard category set whose names are used for categories that have no `name`, by position: "6m" (manufacturing: People, Machine, Method, Material, Measurement, Environment), "8p" (services: Product, Price, Place, Promotion, People, Process, Physical evidence, Productivity), "4s" (service industry: Surroundings, Suppliers, Systems, Skills) or "custom" (unnamed categories show "Category 1", "Category 2"…). Default "6m". A category's own `name` always wins.6m
paletteNoHex colours applied in order to the category bones that have no colour of their own (bone, cause lines and name pill). Pass the user's brand colours here when they name them. Default: indigo, sky, emerald, amber, red, gray.
problemYesThe effect being analysed, shown in the head box at the right end of the spine, e.g. "Late medication administration on Ward 4B". Phrase it as a problem, not a cause. Wraps to 5 lines in the box; about 3–10 words reads best.
categoriesYesThe category bones (1–8; 4–6 is typical), drawn left to right in pairs: the first above the spine, the second below it, the third above, and so on. More than 8 are dropped with a warning. E.g. [{ "name": "People", "causes": [{ "text": "Agency staff unfamiliar with the ward", "sub": ["No induction checklist"] }] }].

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?

Beyond the readOnlyHint and idempotentHint annotations, it discloses generation limits, instructs the agent to infer missing details rather than ask, and explains the Edit link and when to give the user the image link. It also notes that inline chat images usually cannot be saved, which is practical operational context an agent would not otherwise know.

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?

The description is front-loaded with the purpose, then alternatives, limits, and link guidance in a logical order. It is dense and somewhat run-on, with repeated limit statements that also appear in the schema, but nearly every clause carries useful information for selection or invocation.

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?

Given the tool's complexity, rich schema, and annotations, the description covers everything an agent needs: what it draws, when to use it versus alternatives, how to infer missing parameters, and how to deliver the output link. No output schema exists, and the description sufficiently explains what the rendered result is without needing one.

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?

The schema already documents all 8 parameters at 100% coverage, but the description adds meaningful generation guidance by recommending 4–6 categories with 2–4 causes each and by reiterating practical limits like 2–7 word causes. Most remaining parameter detail is duplicative of the schema, so this is an addition rather than a replacement.

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 precise verb and resource: "Generate a slide-deck-quality fishbone diagram (Ishikawa or cause-and-effect diagram)" and immediately explains its visual structure. It distinguishes this tool from closely related siblings such as create_issue_tree, create_mind_map, create_sipoc, and especially create_lab_fishbone.

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 names when to choose this tool (quality, Lean, Six Sigma DMAIC Analyze, healthcare QI, incident reviews) and when to choose alternatives (issue tree for MECE breakdowns, mind map for open brainstorming, SIPOC for process scoping, create_lab_fishbone for lab skeletons). The contrast with create_lab_fishbone is especially clear since the names are similar.

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