Skip to main content
Glama

Pixly

by app.pixly
OverviewDiscussionsAdmin

Virtual Staging

virtual_staging

AI virtual staging: furnish and style an empty (or badly furnished) room photo in a chosen interior design style — also the tool for "redesign this room" or "show this room in another style". HD, watermark-free results. Some stagings also render a free second version: get_job then lists both under versions (the second can take a minute or two longer) — show the user both and let them pick. Costs credits from the user's Pixly balance.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
styleYesInterior style id. One of: modern-minimal, scandinavian, industrial, mid-century-modern, japandi, contemporary, transitional, urban-chic, bauhaus, organic-modern, brutalist, traditional, art-deco, colonial, victorian, french-country, english-cottage, neoclassical, art-nouveau, grandmillennial, hollywood-regency, mediterranean, mediterranean-modern, rustic-farmhouse, bohemian, tropical, family-staging, hygge, wabi-sabi, modern-farmhouse, cottagecore, shabby-chic, cabin-lodge, eclectic, warm-luxury, investor-premium, contemporary-dark, glam, penthouse-modern, hotel-suite, maximalist, coastal, desert-modern, hacienda, pacific-northwest, caribbean-resort, hamptons, moroccan, tuscan, southwestern, asian-zen, coastal-grandmother, cape-cod. When the user has no preference, "modern-minimal" or "scandinavian" suit most listings.
r2PathNoStorage path of a photo already in the user's Pixly library (from list_library, or returned by an upload ticket) — the alternative to imageUrl.
imageUrlNoPublic https URL of the source photo, or a data: URI. Either imageUrl or r2Path is required.
roomTypeNoRoom type hint; omit to let vision infer it from the photo
numImagesNoIgnored — staging always returns one image. Call again for another take.
stagingQualityNoIgnored — the Pro tier is retired. Every staging costs 1 credit and may render a second version on another model for free.
customInstructionsNoOptional extra instructions blended into the staging prompt

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
noteNo
typeNo
errorNo
jobIdYesPass to get_job to poll
statusYespending | processing | completed | failed — anything not completed/failed is still running
createdAtNo
resultUrlsNoPresent when completed; valid 7 days
completedAtNo
creditsChargedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / r2Path / description
      Previous value: -"R2 object path from an upload ticket (the create_upload_ticket tool, or POST /api/v1/uploads over REST) — the alternative to imageUrl when the photo is a local file."New value: +"Storage path of a photo already in the user's Pixly library (from list_library, or returned by an upload ticket) — the alternative to imageUrl."
  2. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "completedAt": {
+      "type": "string"
+    },
+    "createdAt": {
+      "type": "string"
+    },
+    "creditsCharged": {
+      "type": [
+        "number",
+        "null"
+      ]
+    },
+    "error": {
+      "type": "string"
+    },
+    "jobId": {
+      "description": "Pass to get_job to poll",
+      "type": "string"
+    },
+    "note": {
+      "type": "string"
+    },
+    "resultUrls": {
+      "description": "Present when completed; valid 7 days",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "status": {
+      "description": "pending | processing | completed | failed — anything not completed/failed is still running",
+      "type": "string"
+    },
+    "type": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "jobId",
+    "status"
+  ],
+  "type": "object"
+}
  3. Changed3 schema fields changed
    • changedInput schema / properties / r2Path / description
      Previous value: -"R2 object path from an upload ticket (POST /api/v1/uploads) — the alternative to imageUrl when the photo is a local file."New value: +"R2 object path from an upload ticket (the create_upload_ticket tool, or POST /api/v1/uploads over REST) — the alternative to imageUrl when the photo is a local file."
    • changedInput schema / properties / style / description
      Previous value: -"Style id from the Pixly styles catalog (lib/real-estate/styles.ts)"New value: +"Interior style id. One of: modern-minimal, scandinavian, industrial, mid-century-modern, japandi, contemporary, transitional, urban-chic, bauhaus, organic-modern, brutalist, traditional, art-deco, colonial, victorian, french-country, english-cottage, neoclassical, art-nouveau, grandmillennial, hollywood-regency, mediterranean, mediterranean-modern, rustic-farmhouse, bohemian, tropical, family-staging, hygge, wabi-sabi, modern-farmhouse, cottagecore, shabby-chic, cabin-lodge, eclectic, warm-luxury, investor-premium, contemporary-dark, glam, penthouse-modern, hotel-suite, maximalist, coastal, desert-modern, hacienda, pacific-northwest, caribbean-resort, hamptons, moroccan, tuscan, southwestern, asian-zen, coastal-grandmother, cape-cod. When the user has no preference, \"modern-minimal\" or \"scandinavian\" suit most listings."
    • addedInput schema / properties / style / examples
      Added value: +[
+  "modern-minimal",
+  "scandinavian",
+  "industrial",
+  "mid-century-modern",
+  "japandi"
+]
  4. Changed2 schema fields changed
    • addedInput schema / properties / stagingQuality / deprecated
      Added value: +true
    • changedInput schema / properties / stagingQuality / description
      Previous value: -"pro = Nano Banana Pro instead of Nano Banana 2, at 2 credits instead of 1. Same prompt and same 2K output resolution either way — the model is the only difference."New value: +"Ignored — the Pro tier is retired. Every staging costs 1 credit and may render a second version on another model for free."
  5. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already indicate readOnlyHint=false and destructiveHint=false, so the description doesn't need to restate those. The description adds valuable behavioral context: HD and watermark-free results, the possibility of a free second version under `versions`, and that the second version may take longer. It also discloses that numImages and stagingQuality are ignored, which is important behavioral transparency beyond the schema's deprecated flags. Minor gap: doesn't mention what happens if both imageUrl and r2Path are provided, but that's a parameter-level detail.

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 a single paragraph that front-loads the core purpose and then adds practical details. It's slightly dense but every sentence earns its place: purpose, alternative use cases, output quality, version behavior, and cost. The mention of 'get_job then lists both under `versions`' is a bit nested but still clear. Could be split into two sentences for readability, but it's not bloated.

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 the tool's complexity (7 params, output schema present, sibling tools like restyle_room and remove_furniture), the description covers the essential decision points: what it does, when to use it, what to expect in output, and how to handle the second version. The output schema exists, so return values don't need to be described. The credit cost and watermark-free promise are extra context that helps an agent set user expectations. Nothing critical is missing.

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 description coverage is 100%, so the schema already documents all parameters. The description adds value by explaining the style parameter's default recommendation ('modern-minimal' or 'scandinavian' suit most listings') and by clarifying that numImages and stagingQuality are ignored. It also explains the relationship between r2Path and imageUrl as alternatives. This goes beyond the schema's descriptions, which are already detailed.

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 clearly states the tool's function: AI virtual staging that furnishes and styles a room photo in a chosen interior design style. It also explicitly names alternative use cases ('redesign this room' or 'show this room in another style'), which distinguishes it from siblings like restyle_room or remove_furniture. The verb 'furnish and style' is specific and the resource (room photo) is clear.

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?

The description explicitly says this is also the tool for 'redesign this room' or 'show this room in another style', which helps an agent choose it over siblings like restyle_room. It also provides guidance on handling the optional second version: 'show the user both and let them pick'. It mentions credit costs, which is a practical usage consideration. No explicit exclusions, but the context is clear enough.

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

All Pixly toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources