Pixly

Exterior Touch-up

touch_up_exterior

One-click retouch of an exterior listing photo: a natural sky where it is dull, a healthy lawn where the grass is dead, a clean driveway, and bins, hoses and other clutter removed — each only where needed, with the house unchanged. Costs credits from the user's Pixly balance.

Input Schema

TableJSON Schema

Name	Required	Description
`fix`	No	Which areas the tool may touch: 'sky', 'lawn', 'hardscape' (driveway, paths, patio), 'clutter' (bins, hoses, tools, a stray vehicle). Omit for all four; each is fixed only where the photo needs it.
`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.

Output Schema

TableJSON Schema

Name	Required	Description
`note`	No
`type`	No
`error`	No
`jobId`	Yes	Pass to get_job to poll
`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
`creditsCharged`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 23, 2026

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."

Changed1 schema field changedSep 21, 2026

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"
+}

Changed1 schema field changedSep 20, 2026

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."

AddedSep 6, 2026

TDQS

A3.9/5.0

Behavior4/5

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

The description adds valuable behavioral context not present in the annotations: it costs credits from the user's Pixly balance, it acts selectively ('each only where needed'), and it leaves the house unchanged. The annotations already mark it non-read-only and non-destructive, and the description does not contradict them.

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 dense sentence that front-loads the purpose and packages scope, selectivity, and cost efficiently. It is not bloated, though the examples could be slightly trimmed without losing meaning.

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 3-parameter tool with full schema descriptions and an output schema, the description supplies the missing business context: credit cost, selective application, and house preservation. It does not address alternative selection, but that gap belongs to usage guidelines; an agent still has enough to invoke the tool correctly.

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 baseline is 3. The description gives concrete color to the fix values (dull sky, dead grass, clean driveway, bins/hoses), but it largely restates what the schema already documents and adds no new mechanics for r2Path or imageUrl.

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 specific verb and resource: 'One-click retouch of an exterior listing photo,' then enumerates concrete fixes (sky, lawn, driveway, clutter) with the constraint 'with the house unchanged.' This clearly differentiates it from siblings like replace_sky, replace_lawn, and makeover_exterior, which imply broader or full transformations rather than selective touch-ups.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The intended use is implied: an exterior photo needing selective retouching, not full replacement or restaging. However, the description never explicitly names alternatives or exclusion conditions (e.g., use replace_sky for full sky replacement, declutter_photo for interior clutter), so the agent must infer when this tool is preferred over a sibling.

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?