Skip to main content
Glama

Ask ArchiGPT (architecture & design expert)

luw_archigpt

Get AI architectural advice, feng shui, space planning, material and color suggestions, and square-meter estimates from photos or plans. Attach an image to discuss design questions.

Instructions

Ask Luw.ai's ArchiGPT, an AI architect: design advice, feng shui, space planning, material and color suggestions, technical questions, and estimating square meters from a photo or plan. Attach an image to discuss it. Each call is a standalone question, so put the details it depends on into the message. Costs 1 credit per ~3000 words.

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": {
      "message": "<message>"
    },
    "name": "luw_archigpt"
  }
}

Input Schema

NameRequiredDescriptionDefault
imageNoImage to discuss (public https:// link or data: URI; the local npx server also accepts a file path).
messageYesYour question or message, with the details it depends on.
languageNoReply language, e.g. "en" or "tr". Auto-detected when omitted.
persona_idNoPersona to file the question under. It doesn't remember earlier calls.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.3.18
    • changedInput schema / properties / image / description
      Previous value: -"Image to discuss (https:// URL, local file path, or data: URI)."New value: +"Image to discuss (public https:// link or data: URI; the local npx server also accepts a file path)."
    • changedInput schema / properties / persona_id / description
      Previous value: -"Persona that remembers this conversation."New value: +"Persona to file the question under. It doesn't remember earlier calls."
  2. Changed2 schema fields changedv0.3.2
    • removedInput schema / properties / history
      Removed value: -{
      -  "description": "Previous messages of this conversation, oldest first.",
      -  "items": {
      -    "properties": {
      -      "content": {
      -        "type": "string"
      -      },
      -      "role": {
      -        "enum": [
      -          "user",
      -          "assistant"
      -        ],
      -        "type": "string"
      -      }
      -    },
      -    "required": [
      -      "role",
      -      "content"
      -    ],
      -    "type": "object"
      -  },
      -  "maxItems": 50,
      -  "type": "array"
      -}
    • changedInput schema / properties / message / description
      Previous value: -"Your question or message."New value: +"Your question or message, with the details it depends on."
  3. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

The annotations already flag openWorldHint=true, non-idempotent, non-read-only, non-destructive. The description adds genuinely new behavior: a credit cost model (~1 credit per 3000 words) and that each call is a standalone question with no memory across calls. It does not describe the shape of the reply (text vs. image), which is the main remaining gap.

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?

Three sentences, front-loaded with the capability list followed by usage (image attachment), statelessness, and cost. Every sentence carries information an agent needs and nothing is padded.

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?

For a four-parameter, stateless expert-consultation tool with no output schema, the description covers purpose, image handling, statelessness, and cost. It could go one step further by saying what the response contains (advice text, estimates), which matters since no output schema exists.

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 four parameters are already documented, including the persona_id note that it doesn't remember earlier calls and the image link/data-URI format. The description only reinforces statelessness and image attachment, adding little semantics beyond the schema; baseline 3 applies.

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?

The description names a specific resource (Luw.ai's ArchiGPT) and enumerates concrete capability domains: design advice, feng shui, space planning, material/color suggestions, technical Q&A, and square-meter estimation from a photo. This clearly separates it from sibling image-generation tools like luw_interior_design, though it never names an alternative explicitly.

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?

"Attach an image to discuss it" and "put the details it depends on into the message" give actionable invocation guidance, including the important constraint that calls are stateless. It stops short of stating when to prefer this over the design-generation siblings, so there are no explicit exclusions.

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