Skip to main content
Glama
Pedra MCP Server

Pedra MCP Server

Official
by pedra-ai

Stage one room from several angles

pedra_furnish_same_room

Virtually stage 2–10 photos of the same room from different angles with identical furniture and layout, so every image matches. Use instead of per-photo staging to keep one room consistent.

Instructions

Virtually stage 2 to 10 photos of the SAME room, taken from different angles, so every photo gets the same furniture in the same places. Stages the first photo in the given style, then furnishes every other angle from it (or from referenceImageUrl if the room is already staged). Use this instead of calling pedra_furnish per photo whenever the user has several shots of one room: pedra_furnish would give each photo different furniture. Put the widest shot first. Costs 1 credit for the first photo and 2 per extra angle. Runs in the background: returns a jobId right away; call pedra_get_furnish_same_room with it until status is ready.

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": {
      "imageUrls": "<imageUrls>"
    },
    "name": "pedra_furnish_same_room"
  }
}

Input Schema

NameRequiredDescriptionDefault
styleNoStyle for the first photo, e.g. "Minimalist", "Scandinavian". Required unless referenceImageUrl is set.
roomTypeNoe.g. "Living room", "Bedroom". Auto-detected if omitted.
imageUrlsYes2 to 10 photos of one room, widest shot first: public https:// URLs, data: URIs, or absolute paths to local image files on this computer. One room per call: stage the living room and the bedroom as separate calls.
propertyIdNoOptional id of the Pedra property (from pedra_list_properties) this photo belongs to. When set, the result is saved into that property's gallery — visible and editable from the app — instead of only being returned as a URL.
referenceImageUrlNoOptional public URL of a photo of this room that is already staged. Every photo in imageUrls is then furnished to match it (2 credits each) and style is ignored.
preserveAspectRatioNoBy default the output comes back at whatever size the AI model produces, which may not match the input's aspect ratio or resolution. Set to true to get the result at the exact width and height of the input image (center-cropped to the original aspect ratio, never stretched). Defaults to false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.8.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare readOnly=false, openWorld=true, destructive=false; the description adds the material behavior an agent cannot infer: a credit cost model (1 for the first photo, 2 per extra angle, 2 each when referenceImageUrl is used) and a background-execution contract (returns a jobId immediately, poll pedra_get_furnish_same_room until status is ready). That is exactly the context needed to plan cost and handle an async result.

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?

The description is front-loaded with the core purpose, then the alternative, ordering, cost, and async flow in a logical sequence with no filler sentences. It is on the long side and restates a couple of schema details (widest shot first, style ignored), which keeps it from a 5.

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 multi-image, costly, asynchronous generation tool with no output schema, it covers everything the agent needs: input constraints, the polling follow-up, the cost, the sibling alternative, and the persistence option via propertyId. No material gap remains.

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; the description earns an extra point by attaching pricing to the parameter choice (referenceImageUrl makes each photo 2 credits and voids style) and by stating the practical constraint of one room per call. It does, however, repeat schema-stated facts like widest-shot-first and style being ignored.

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?

The description opens with a specific verb plus resource plus scope: virtually stage 2–10 photos of the SAME room from different angles so all get identical furniture. It immediately distinguishes itself from pedra_furnish, which would produce inconsistent furniture per photo.

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?

It gives an explicit use condition (multiple shots of one room), an explicit alternative to avoid (calling pedra_furnish per photo) with the reason why, and an ordering rule (widest shot first). Nothing about when to pick this over its sibling is left to inference.

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