Skip to main content
Glama
Sign In

Pixly

by app.pixly
OverviewDiscussionsAdmin

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

NameRequiredDescriptionDefault
fixNoWhich 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.
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.
listingIdNoA 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

NameRequiredDescriptionDefault
jobsNoSeveral jobs at once (get_job with jobIds, or a plan's steps): each one's jobId, status and results
noteNo
typeNo
errorNo
jobIdYesPass to get_job to poll
quoteNoPresent when status is "awaiting_confirmation": nothing ran and nothing was charged yet — the price and settings the user is asked to confirm
statusYespending | processing | completed | failed — anything not completed/failed is still running
createdAtNo
resultUrlsNoPresent when completed; valid 7 days
completedAtNo
resultPathsNoStorage path of each result — pass one as r2Path (or beforeR2Path, a photos[] item) to run another tool on this result
creditsChargedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • 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"
+}
  2. Changed1 schema field changed
    • 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"
+}
  3. Changed1 schema field changed
    • 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"
+}
  4. 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."
  5. 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"
+}
  6. Changed1 schema field 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."
  7. Added

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already cover the safe/non-destructive profile, and the description adds real value beyond them: the credit cost against the user's Pixly balance and the conservative behavioral guarantees ('each only where needed', 'the house unchanged'). It does not disclose asynchronous/job processing, which is a notable omission given the sibling get_job, but with a job-style output schema this is a minor gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with the action and scope front-loaded, then a short cost note. The enumeration of effects is informative rather than padding, and nothing is wasted.

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 an output schema present and annotations covering safety, the description sufficiently covers what the tool does, its credit cost, and its conservative scope. The main missing piece is whether invocation is asynchronous/returns a job, which matters in a system with get_job polling.

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 coverage is 100%, so the schema already documents all four parameters including the 'fix' enum values and the imageUrl/r2Path relationship. The description adds no format, default, or precedence detail beyond what the schema states, so the baseline 3 is correct.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb (retouch) and resource (exterior listing photo) and enumerates the exact effects (sky, lawn, driveway, clutter removal), so the purpose is concrete. It never explicitly separates itself from overlapping siblings like replace_sky, replace_lawn, declutter_photo, or makeover_exterior, so an agent must infer that this is the combined one-click variant.

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 phrase 'one-click' and 'each only where needed' implies when this tool is preferred (a single combined pass rather than per-area tools), but there is no explicit when-to-use, no exclusions, and no named alternative. Usage is left to inference rather than stated.

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