Pixly

Before & After Image

before_after_image

Free (no credits): one comparison image from a before and an after photo of the same place — e.g. an empty room and its virtual staging, a daylight shot and its dusk version, a room before and after a restyle. Side by side, stacked, or split by a line; original shape, square, 4:5 or 9:16. Write the labels in the user's language. Returns a finished image at once.

Input Schema

Name	Required	Description	Default
`aspect`	No	Shape of the image: original (follows the photos), 1:1 square, 4:5 Instagram post, 9:16 Stories/Reels.	original
`labels`	No	Show the Before / After labels.
`layout`	No	side = next to each other, stack = one above the other, vsplit = one frame split by a vertical line, diagonal = split by a slanted line.	side
`listingId`	No	A property folder (from list_listings or create_listing) to put the result in. Results of a photo that is already in a folder go there by themselves.
`afterLabel`	No	Label text for the after photo, in the user's language (default "After").
`afterR2Path`	No	Storage path of the after photo — the alternative to afterImageUrl.
`beforeLabel`	No	Label text for the before photo, in the user's language (default "Before").
`beforeR2Path`	No	Storage path of the before photo — the alternative to beforeImageUrl. For a Pixly result, its original photo is the job's source.
`afterImageUrl`	No	The AFTER photo (e.g. the staged room, the dusk version). Public https URL or data: URI; or afterR2Path.
`beforeImageUrl`	No	The BEFORE photo (e.g. the empty room, the daylight shot). Public https URL or data: URI; or beforeR2Path.

Output Schema

Name	Required	Description
`jobs`	No	Several jobs at once (get_job with jobIds, or a plan's steps): each one's jobId, status and results
`note`	No
`type`	No
`error`	No
`jobId`	Yes	Pass to get_job to poll
`quote`	No	Present when status is "awaiting_confirmation": nothing ran and nothing was charged yet — the price and settings the user is asked to confirm
`status`	Yes	pending \| processing \| completed \| failed — anything not completed/failed is still running
`createdAt`	No
`resultUrls`	No	Present when completed; valid 7 days
`completedAt`	No
`resultPaths`	No	Storage path of each result — pass one as r2Path (or beforeR2Path, a photos[] item) to run another tool on this result
`creditsCharged`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 11, 2026

addedInput schema / properties / listingId

Added value: +{
+  "description": "A property folder (from list_listings or create_listing) to put the result in. Results of a photo that is already in a folder go there by themselves.",
+  "type": "string"
+}

addedOutput schema / properties / jobs

Added value: +{
+  "description": "Several jobs at once (get_job with jobIds, or a plan's steps): each one's jobId, status and results",
+  "items": {
+    "type": "object"
+  },
+  "type": "array"
+}

Changed1 schema field changedOct 6, 2026

addedOutput schema / properties / quote

Added value: +{
+  "description": "Present when status is \"awaiting_confirmation\": nothing ran and nothing was charged yet — the price and settings the user is asked to confirm",
+  "type": "object"
+}

Changed1 schema field changedOct 2, 2026

addedOutput schema / properties / resultPaths

Added value: +{
+  "description": "Storage path of each result — pass one as r2Path (or beforeR2Path, a photos[] item) to run another tool on this result",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

AddedOct 2, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare non-read-only, non-idempotent, non-destructive, open-world behavior. The description adds two useful facts beyond them: it is credit-free, and it returns synchronously ('Returns a finished image at once'), which tells the agent not to poll for a job. It stops short of stating whether repeated calls produce new artifacts, which the non-idempotent hint would make relevant.

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?

One densely packed sentence, front-loaded with the most decision-relevant token ('Free (no credits)') and closing with the output/timing statement. Every clause carries information, though the enumeration of examples and layout/aspect forms duplicates schema enums and could be tightened.

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 10 parameters, 100% schema coverage, an output schema present, and annotations covering the safety profile, the description supplies what structured fields cannot: the free-of-cost condition, the synchronous return, and the paired-photo premise. Nothing essential for correct invocation is missing; only explicit sibling routing is absent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although schema coverage is already 100%, the description adds genuine semantics beyond the schema: it declares the implicit requirement of a before/after pair of the same place (which 0-required-parameter schema does not enforce) and reiterates the label-language rule. The layout and aspect options it mentions ('side by side, stacked, or split by a line; original shape, square, 4:5 or 9:16') map to enum values already documented, so the added value sits mainly in the input-pairing constraint.

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 states a concrete verb and artifact: it produces 'one comparison image from a before and an after photo of the same place', backed by three concrete example pairs (empty room/staged, daylight/dusk, before/after restyle). It also names the output medium ('a finished image at once'), which implicitly separates it from the sibling before_after_reel. An agent can identify the resource and result type without opening the schema.

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?

It gives rich when-to-use context in the form of scenario examples ('an empty room and its virtual staging', 'a daylight shot and its dusk version') and flags a cost condition ('Free (no credits)'). However, it never states when to choose this over alternatives like before_after_reel or day_to_night, nor any exclusions or prerequisites, so selection guidance is contextual rather than explicit.

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

All Pixly tools Inspect

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

Need Help?