Skip to main content
Glama
Sign In
ArchScript MCP

ArchScript MCP

by schlummer13
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

Export

export
Read-only

Generate Mermaid, PlantUML, Markdown, JSON, or AWS/Azure/GCP Terraform output from a valid architecture document.

Instructions

Generated output of a valid document: mermaid, plantuml, markdown (documentation), json (model) or terraform_aws / terraform_azure / terraform_gcp.

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": {
      "format": "<format>"
    },
    "name": "export"
  }
}

Input Schema

NameRequiredDescriptionDefault
formatYes
documentNoDocument id (e.g. doc1), file name or project name. Omit for the frontmost document.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.7/5.0
Behavior2/5

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

Annotations already declare readOnlyHint=true, so the safety profile is covered, and the description contradicts nothing. However, beyond repeating the enum of formats it adds almost no behavioral context – nothing about what 'valid' means, what happens on an invalid or missing document, or whether the document parameter accepts ids vs file names.

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?

A single sentence with no filler, front-loading the format list. The phrasing is slightly awkward and reads more like a field description than an action statement, but nothing is wasted.

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

Completeness3/5

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

For a simple read-only, two-parameter tool with no output schema, the description covers what kinds of output exist but not what the actual return value looks like or what makes a document 'valid'. Adequate but leaves meaningful gaps an agent would hit when invoking it.

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 50%; the document parameter is already described in the schema including the 'omit for frontmost document' behavior. The description's only added value is hinting at what each format yields (markdown=documentation, json=model, terraform_* variants), which lightly disambiguates the enum choices but does not fully compensate for the undocumented format field.

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

Purpose3/5

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

The description names the resource (generated output of a document) and enumerates the formats, which helps differentiate it from siblings like render_diagram, but the phrasing 'Generated output of a valid document' is a noun phrase rather than a clear verb+object statement of what the tool does. An agent can guess this produces an export, but the action itself is only implied by the tool name.

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

Usage Guidelines2/5

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

There is no explicit when-to-use guidance, no mention of when to prefer export over render_diagram or review, and no stated prerequisites beyond the vague 'valid document' qualifier. The agent must infer that the document should be validated first and that this is a read-only generation step.

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

Deploy Server

Other Tools