Skip to main content
Glama
cloudsketch-mcp

cloudsketch-mcp

Official

Generate a diagram

generate_diagram

Convert a plain-English system or process description into accurate Mermaid diagram code, choosing from architecture, database, UML, and process diagram types.

Instructions

Turn a plain-English description of a system, database, process or plan into an accurate diagram (Mermaid code) with CloudSketch AI. Uses credits from the CloudSketch AI account that owns the API token. Describe the real system in detail: components, data stores, external services, users, and the cloud or country if relevant.

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": {
      "description": "<description>",
      "diagram_type": "<diagram_type>"
    },
    "name": "generate_diagram"
  }
}

Input Schema

NameRequiredDescriptionDefault
audienceNotechnical (default): exact technical names. managers: plain words. investors: business view.
descriptionYesWhat to draw, in plain English (20-4000 characters). Be specific.
diagram_typeYesWhich kind of diagram. Use list_diagram_types if unsure.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

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

Adds genuinely useful context beyond the annotations: that the call draws down credits from the CloudSketch AI account owning the API token, and that output is Mermaid code. This complements readOnlyHint=false and openWorldHint=true without restating them. It does not say whether credits are consumed on failure, how many, or whether the result is persisted versus returned inline.

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?

Three sentences, front-loaded with verb, resource and output format; the credit-cost sentence follows and the input-shaping sentence closes. Each sentence carries distinct information, though 'with CloudSketch AI' and the credit sentence overlap slightly on branding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly compensates by naming the return format (Mermaid code), and it discloses the credit cost of a non-read-only generation call. What's missing is small but real: whether output is returned inline or must be opened via open_in_cloudsketch, and typical latency or length limits.

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?

Schema coverage is 100%, so the baseline is 3, and the description earns one above it by telling the agent what content to put in the description parameter — the actual system's components, data stores, external services, users, and cloud/country. It adds little for audience and diagram_type, which the enums already document well.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific transformation: plain-English system description in, an accurate diagram as Mermaid code out, attributed to CloudSketch AI. That clearly distinguishes it from list_diagram_types and check_credits, though sibling differentiation appears only indirectly via the schema's 'Use list_diagram_types if unsure' note rather than in the description.

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

Usage Guidelines3/5

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

Gives input-preparation guidance ('Describe the real system in detail: components, data stores, external services, users, and the cloud or country if relevant'), which implies when the tool works well. It never states when not to use it or names an alternative path, so an agent must infer that list_diagram_types precedes it when the diagram type is unclear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.