Skip to main content
Glama

Photo AI Studio

by com.photoaistudio

Edit a photo

edit_image

Edit a photo with one of 19 AI operations. Credit costs: remove_background 10, replace_background 3, everything else 100.

Operations and their required arguments:

  • remove_background (image_url)

  • replace_background (image_url, prompt)

  • retouch (image_url, prompt)

  • skin (image_url)

  • hair (image_url, plus hairstyle or reference_image_url)

  • makeup (image_url)

  • age (image_url, target_age)

  • expression (image_url, target_expression)

  • body_type (image_url, target_body_type)

  • eye_color (image_url, target_eye_color)

  • color_correction (image_url)

  • custom (image_url, prompt)

  • clothes (image_url, clothes_image_url)

  • try_on (image_url, clothes_image_url)

  • product (image_url, product_image_url)

  • upscale (image_url)

  • restore (image_url)

  • face_swap (source_image_url, target_image_url)

  • extend (image_url)

Every image argument must be a CDN URL from upload_image.

Requires a connected Photo AI Studio account. Calling this tool starts the sign-in flow.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
promptNoText prompt for replace_background, retouch, and custom
hairstyleNoTarget hairstyle for the hair operation
image_urlNoCDN URL of the image to edit, required for every operation except face_swap
operationYesThe edit operation to perform
hair_colorNoTarget hair color for the hair operation
num_imagesNoNumber of variations for try_on (1-4)
target_ageNoTarget age for the age operation
wait_for_resultNoWait up to 55 seconds for the result before returning. Defaults to false: the tool returns a prediction_id immediately and you poll get_prediction, which is the reliable pattern for photos and videos.
source_image_urlNoSource face image for face_swap
target_body_typeNoTarget body type
target_eye_colorNoTarget eye color
target_image_urlNoTarget image for face_swap
clothes_image_urlNoClothes image for clothes and try_on
product_image_urlNoProduct image for the product operation
target_expressionNoTarget expression, for example "happy"
reference_image_urlNoReference image for hair or custom

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Beyond the annotations (readOnly=false, destructive=false), it discloses credit costs per operation, the sign-in side effect, and the CDN-URL requirement. It could also describe the asynchronous output/polling behavior, which is absent from the main description, so it is not a perfect 5.

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 long but scannable: cost summary first, then a bulleted operation list, then constraints. Each section earns its place, though a compact return-value or polling note could make it tighter.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 19 operations, 16 parameters, and no output schema, the description covers operations, costs, auth, and URL constraints well. However, it never explains what the tool returns (e.g., a prediction_id or polling with get_prediction), leaving a meaningful gap for an agent.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds a valuable operation-to-argument matrix and the global CDN constraint. It omits optional parameters like hair_color and num_images from the list, but it clearly covers the required argument relationships.

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 opens with 'Edit a photo with one of 19 AI operations' and then enumerates every operation, making the resource and action unambiguous. This clearly differentiates it from siblings like generate_photo, upload_image, and create_video.

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 establishes a clear use context: edit existing photos with one of these specific operations, and sets prerequisites such as 'Every image argument must be a CDN URL from upload_image' and 'Requires a connected Photo AI Studio account.' It does not explicitly name sibling alternatives or when-not-to-use cases, so it stops short of 5.

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

All Photo AI Studio toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.2/5.0
Disambiguation4/5

Most tools are clearly distinct by resource and action, but browse_themes and list_photo_themes have overlapping names and both deal with themes, requiring careful description reading to pick correctly. The other informational tools (get_api_capabilities, get_service_overview, get_pricing) are also similar in style but serve clearly different purposes.

Naming Consistency5/5

All tool names follow a consistent snake_case verb_noun pattern (browse, create, edit, generate, get, list, upload). There are no style mixes or vague verbs, making the naming predictable and easy to navigate.

Tool Count5/5

With 12 tools, the set is well within the ideal 3–15 range and each tool earns its place by covering a distinct part of the photo/video generation workflow, from uploading and generating to checking predictions and managing account/cost information.

Completeness5/5

The tool surface covers the full generation lifecycle: upload, generate/edit/video, poll results, list history, account status, pricing, themes, and API guidance. There are no obvious dead ends or missing operations that would prevent an agent from completing a realistic photo editing or generation workflow.

Resources