Skip to main content
Glama

Create flowchart

create_flowchart
Read-onlyIdempotent

Turn Mermaid flowchart or graph syntax, or an indented outline, into FlowSimp links. Use it when the steps already exist as text and someone needs a diagram they can view or edit. Returns JSON with shareUrl (a read-only /view# link), editUrl (opens the editor at /?board=), nodeCount, and connectionCount. An optional title is echoed in that JSON; it is not drawn on a shape. The diagram is compressed into the link, so nothing is stored and the call does not write to a database. Only flowchart and graph syntax are accepted. Other Mermaid types are refused. Text is limited to 16,000 characters and about 80 shapes.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "text": "<text>"
    },
    "name": "create_flowchart"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoEditor mode stored in the link. flowchart is the default. network opens the network editor instead. Parsing does not change with the mode.
textYesDiagram source. A Mermaid flowchart or graph (flowchart TD, rectangles in [], diamonds in {}, edge labels such as -->|Yes|), or an indented outline with one step per line. A trailing question mark becomes a decision, and Yes: or No: becomes an arrow label. Required. Maximum 16,000 characters.
titleNoOptional label echoed in the JSON result. It is not placed on a shape and it is not stored.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / mode / description
      Previous value: -"Editor mode. Defaults to flowchart."New value: +"Editor mode stored in the link. flowchart is the default. network opens the network editor instead. Parsing does not change with the mode."
    • changedInput schema / properties / text / description
      Previous value: -"Mermaid flowchart or an indented outline, up to 16,000 characters."New value: +"Diagram source. A Mermaid flowchart or graph (flowchart TD, rectangles in [], diamonds in {}, edge labels such as -->|Yes|), or an indented outline with one step per line. A trailing question mark becomes a decision, and Yes: or No: becomes an arrow label. Required. Maximum 16,000 characters."
    • changedInput schema / properties / title / description
      Previous value: -"Optional title. Included in the text summary only."New value: +"Optional label echoed in the JSON result. It is not placed on a shape and it is not stored."
  2. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Goes well beyond the readOnly/idempotent annotations by explaining that the diagram is compressed into the link, nothing is stored, and no database write occurs — resolving the apparent tension between 'create' and readOnlyHint. It also discloses hard limits (16,000 characters, ~80 shapes) and the exact JSON fields returned, which matters since there is no output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Short declarative sentences, front-loaded with the core transformation, followed by usage, return shape, storage behavior, and limits in a logical order. No filler.

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 no output schema, the description compensates by naming shareUrl, editUrl, nodeCount, and connectionCount, and it covers input constraints, accepted syntax, and persistence behavior. An agent has everything needed to call this correctly.

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 coverage is 100%, so all three parameters are already documented in the schema. The description reinforces that title is only echoed in JSON and not drawn, but that duplicates the schema text rather than adding new semantics; mode is not discussed at all in the description.

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: turning Mermaid flowchart/graph syntax or an indented outline into FlowSimp links. The scope is narrow enough to distinguish it from the only sibling, list_templates, which has nothing to do with diagram creation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says when to use it ("when the steps already exist as text and someone needs a diagram they can view or edit") and states what is rejected (other Mermaid types). It doesn't compare against alternatives, but the lone sibling is unrelated, so the missing comparison costs little.

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.