Skip to main content
Glama

Two Minute Lab Fishbone

create_lab_fishbone
Read-onlyIdempotent

Generate clean lab fishbone diagrams (lab value skeletons), the shorthand nurses, residents and students use in notes and case presentations: BMP / Chem-7 (Na | Cl | BUN over K | HCO3 | Cr with glucose in the tail), CBC (WBC > Hgb over Hct < Plt), coags (PT | PTT over INR), LFT (TP | AST | T bili over Alb | ALT | ALP), ABG (pH / pCO2 / pO2 / HCO3) and Ca/Mg/Phos, each with an optional caption such as a time, in a tidy grid. Numeric values outside adult reference ranges are flagged red with ↑ or blue with ↓ (US or SI ranges; overridable per value), and the result also includes a plain-text version to paste into a note. Choose it whenever lab results should be shown in fishbone form; it is not a cause-and-effect (Ishikawa) diagram, for which use create_fishbone. Values are strings of up to 8 characters; 1–8 panels. A drawing aid only, not clinical decision support: never include patient names or identifiers, because links carry the data. 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": "Day 3 labs",
      "panels": [
        {
          "k": "5.6",
          "cl": "102",
          "cr": "1.1",
          "na": "138",
          "bun": "18",
          "glu": "112",
          "hco3": "24",
          "type": "bmp",
          "caption": "06:00"
        },
        {
          "hct": "39.5",
          "hgb": "13.2",
          "plt": "245",
          "wbc": "8.4",
          "type": "cbc",
          "caption": "06:00"
        }
      ]
    },
    "name": "create_lab_fishbone"
  }
}

Input Schema

NameRequiredDescriptionDefault
flagNoFlag numeric values outside the adult reference range: red with ↑ when high, blue with ↓ when low. Default true. Manual `flags` on a panel apply either way. Ranges vary by lab; this is a drawing aid, not clinical decision support.
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 at 22px bold, e.g. "Day 3 labs". An empty string hides it. Never put a patient name or identifier here: links carry the chart itself.Labs
unitsNoWhich reference ranges the automatic flags use: "US" (conventional units: mg/dL, g/dL, %, mmHg; the default) or "SI" (mmol/L, µmol/L, g/L, L/L, kPa). It does not convert values.US
widthNoChart width in pixels (640–2400). Omit it (recommended) and the chart sizes itself to its content with comfortable margins, between 880 and 1280px wide. PNG output renders at 2x.
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).
labelsNoShow a small analyte name (Na, K, Hgb…) beside every value. Default false: experienced readers know the positions; turn it on for teaching or for readers new to the shorthand.
panelsYesThe panels to draw (1–8), in order, two or three per row. Each has a `type` and its values as flat string keys; leave a key out to leave its position blank. More than 8 are dropped.
paletteNoHex colours; only the first is used, for the small panel-type tags. The skeletons stay monochrome, and flags are always red (high) and blue (low).

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/openWorld=false/idempotent, so the description carries the rest and does it well: it discloses the automatic red/blue flagging with US or SI ranges and per-value override, that a plain-text version is also returned, the 1–8 panel and 8-character value limits, the builder Edit link, and that links carry the data. The safety framing ("drawing aid only, not clinical decision support: never include patient names or identifiers") is exactly the kind of constraint annotations cannot express.

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?

Core purpose and the sibling exclusion lead, and the closing sentence on the image link is high-value operational guidance. It is a single dense wall of text, though, with the panel enumeration restating schema content and the analyte layouts repeated in the parameter descriptions — a bulleted or shorter treatment would be easier to parse without losing meaning.

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 9-parameter, 100%-documented, read-only generation tool with no output schema, the description covers everything an agent needs: what is drawn, how values are flagged, unit systems, panel count limits, the non-clinical framing, and what the caller should do with the returned link. The absence of an output schema is partly offset by the description stating that a plain-text rendering and a link are returned.

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 `flag`, `units`, `look`, `flags`, `panels`, and every analyte key in detail. The description adds only light framing — "overridable per value" points at `flags`, and the parenthetical layouts map analytes to positions — but it does not explain parameter usage beyond what the schema states. Baseline 3 is appropriate when the schema does the heavy lifting.

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 clean lab fishbone diagrams") and immediately enumerates the exact panel skeletons produced (BMP, CBC, coags, LFT, ABG, Ca/Mg/Phos) with their layout. It also explicitly excludes the nearest sibling: "it is not a cause-and-effect (Ishikawa) diagram, for which use create_fishbone." An agent can distinguish this from every other create_* sibling 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?

"Choose it whenever lab results should be shown in fishbone form" gives the positive trigger, and the create_fishbone exclusion gives the negative case. It goes further with operating guidance an agent wouldn't otherwise have: "Infer missing details rather than asking; the user can adjust the chart in the builder" and "ALWAYS give the user the image link" with the reason (inline chat images usually cannot be saved).

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