Magic Hour

AI Face Editor

ai_face_editor_edit_image

MCP guidance:

Starts an async image job; returns id and credits_charged. For finished results, call wait_for_image_project with that id or poll GET /v1/image-projects/{id} until complete, error, or canceled. Results include downloads; wait helpers add exact_download_urls. Preserve signed URLs and query parameters; never append expiration metadata.
For *_file_path, use an existing Magic Hour path or the upload-URL endpoint's file_path after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure.

Edit facial features of an image using AI. Each edit costs 1 frame. The height/width of the output image depends on your subscription. Please refer to our pricing page for more details

Input Schema

Name	Required	Description	Default
`name`	No	Give your image a custom name for easy identification.	Face Editor - dateTime
`style`	Yes	Face editing parameters
`assets`	Yes	Provide the assets for face editor

Output Schema

Name	Required	Description	Default
`id`	Yes	Unique ID of the image. Use it with the [Get image Project API](https://docs.magichour.ai/api-reference/image-projects/get-image-details) to fetch status and downloads.
`credits_charged`	Yes	The amount of credits deducted from your account to generate the image. We charge credits right when the request is made. If an error occurred while generating the image(s), credits will be refunded and this field will be updated to include the refund.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 24, 2026

removedInput schema / properties / context

Removed value: -{
-  "description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\"",
-  "type": "string"
-}

Changed1 schema field changedSep 11, 2026

addedInput schema / properties / context

Added value: +{
+  "description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\"",
+  "type": "string"
+}

First observedSep 1, 2026

TDQS

A4.2/5.0

Behavior5/5

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false) the description discloses that this is an async job, that it returns id and credits_charged, the terminal status values (complete, error, canceled), that results carry downloads (with exact_download_urls from wait helpers), the cost of 1 frame per edit, and a signed-URL preservation warning. That is unusually rich behavioral context.

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 guidance is front-loaded into two dense bullets covering result retrieval and file-path handling, followed by the one-line purpose statement. It is on the long side and the pricing/subscription sentence is partly promotional, but nearly every clause carries operational information.

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 nested-schema, async, paid mutation tool with an output schema and annotations, the description covers the full lifecycle: submit, cost, poll/wait, and result retrieval, plus file-path handling. The only substantive gap is sibling disambiguation within the create_image family.

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 already 100%, so the baseline is 3, but the guidance adds real meaning for image_file_path: direct public media URLs 'may work if stable and fetchable as raw bytes', hotlinked URLs can fail, and the upload-URL endpoint is preferred when uncertain. The style parameters are left entirely to the schema, which is acceptable given its completeness.

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?

The description states a specific verb and resource: 'Edit facial features of an image using AI', backed by the schema's expression parameters (head_yaw, mouth_smile, eye_gaze). It is clearly distinguishable in intent, but it never names or contrasts with the many close siblings (face_swap_photo_create_image, head_swap_create_image, body_swap_create_image), so an agent must infer the boundary itself.

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 gives explicit conditional guidance: call wait_for_image_project with the returned id or poll GET /v1/image-projects/{id}, and 'Prefer the upload-URL endpoint when unsure' for file paths, with the caveat that hotlinked URLs can fail. What is missing is any when-to-use-this-tool-versus-siblings routing, which is notable given the crowded create_image family.

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

All Magic Hour 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?