Remove clutter, mess, and personal items from a listing photo while keeping the room, furniture, and architecture intact. Costs credits from the user's Pixly balance.
| Name | Required | Description | Default |
|---|---|---|---|
| r2Path | No | R2 object path from an upload ticket (POST /api/v1/uploads) — the alternative to imageUrl when the photo is a local file. | |
| imageUrl | No | Public https URL of the source photo, or a data: URI. Either imageUrl or r2Path is required. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds meaningful behavioral context beyond the annotations by disclosing the credit cost from the user's Pixly balance. It also emphasizes preservation of room/furniture/architecture, which clarifies the non-destructive nature. It does not detail output format or reversibility, but the annotations already cover the read-only/destructive flags.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences: the first states the core purpose, and the second states the credit cost. There is no wasted wording, and the important information is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the core behavior and cost but lacks any mention of the return value or post-operation result (e.g., does it return an edited image URL or a job ID?). Given there is no output schema and the tool has a side effect (credit deduction), this missing information is a gap, keeping the score at a minimum viable level.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already describes both parameters (r2Path and imageUrl) with 100% coverage, including the alternative requirement. The description adds no additional parameter-specific meaning, so the baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: 'Remove clutter, mess, and personal items from a listing photo' with the specific constraint of 'keeping the room, furniture, and architecture intact.' This verb+resource phrasing distinguishes it from sibling editing tools like virtual_staging or enhance_photo.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It implies a clear use case (listing photos with unwanted clutter) and notes that credits are consumed, which is an operational consideration. However, it does not explicitly compare to alternatives or state when not to use it, so it falls short of the top score.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct workflow: uploads, job/credit management, single-effect photo edits, staging, and video generation. The only mild ambiguity is between declutter_photo and remove_furniture, but the descriptions explicitly contrast them, so an agent can usually pick correctly.
Most tools follow a clear verb_noun snake_case pattern like create_upload_ticket, replace_sky, and remove_furniture. A few names are noun phrases rather than verbs—day_to_night, virtual_staging, before_after_reel—but they are still readable and do not break the overall convention badly.
At 15 tools, the server is at the upper edge of the ideal range, but every tool maps to a distinct real-estate photo/video workflow: uploading, credits, job polling, staging, editing, and reveal videos. Nothing feels redundant or unnecessary.
The core Pixly workflow is well covered: bring images in via upload, run generation/editing tools, poll jobs, and list results. Minor gaps like job cancellation or generic restyle control exist, but agents can complete the primary photo and video workflows end to end.
