Pixly

Straighten Photo

straighten_photo

Free (no credits): automatically straighten a property photo — leaning walls made vertical (converging verticals from a tilted camera) and a tilted horizon levelled, like a pro photographer's lens correction. Crops the edges slightly. Best before staging or any other edit. Says so when the photo is already straight or has no straight lines to go by.

Input Schema

Name	Required	Description
`r2Path`	No	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.
`imageUrl`	No	Public https URL of the source photo, or a data: URI. Either imageUrl or r2Path is required.
`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.

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

A4.2/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), but the description adds material context beyond them: it is free/no credits, it crops the edges slightly (a real side effect of a non-destructive write), and it reports when no straightening was possible. That is behavior an agent could not infer from the schema.

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?

Front-loaded with the cost and the core action, and every clause (mechanism, side effect, ordering advice, edge case) earns its place. The heavy use of em-dash asides makes it slightly denser to parse than it needs to be.

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?

With an output schema present, return values need no explanation. For a 3-parameter tool with full schema coverage, the description covers cost, mechanism, side effects, sequencing, and the degenerate-input case — nothing an agent needs in order to call it correctly is missing.

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 description coverage is 100%, so the schema already documents r2Path, imageUrl, and listingId in detail. The description adds no parameter syntax or format meaning, which is the baseline-3 case when the schema does the heavy lifting.

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?

Specific verb+resource ("straighten a property photo") with the exact mechanism spelled out: leaning walls made vertical from converging verticals and a tilted horizon levelled. This clearly distinguishes it from siblings like enhance_photo, upscale_hd, or edit_staged_photo.

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?

"Best before staging or any other edit" gives real sequencing guidance that shapes how an agent orders its calls, and the edge-case clause ("says so when the photo is already straight") sets expectations. It stops short of naming an alternative or stating when not to use it, so it doesn't reach 5.

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?