Skip to main content
Glama

Lumethic Photo Verification

by com.lumethic
OverviewDiscussionsAdmin

verify_photo

Verify a photo's authenticity from a RAW camera file and its JPEG export, when the user asks for proof or a check that the photo is a genuine camera capture (not for feedback on the photo itself). Provide the files as attachments (raw_file = the camera RAW such as .CR2/.CR3/.NEF/.ARW/.RAF/.ORF/.DNG, image_file = the exported .jpg/.png), inline as raw_base64 + image_base64 (small files), or — for large files without attachments — call create_verification_upload first and pass the returned raw_object_key + image_object_key. Returns a verification id at once; the analysis runs in the background and takes from about a minute to 10 minutes or more, so call get_verification with the id repeatedly until status is completed. Counts against the monthly quota (free tier: 5/month).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
raw_fileNoThe camera RAW file the user attached (.CR2/.CR3/.NEF/.ARW/.RAF/.ORF/.DNG ...); its file_name selects the decoder.
image_fileNoThe JPEG/PNG export of the same shot the user attached; pairs with raw_file.
raw_base64NoThe camera RAW file as base64, for files up to a few MB. For larger files call create_verification_upload and pass raw_object_key instead.
image_base64NoThe JPEG export of the same shot as base64; pairs with raw_base64.
raw_filenameNoOriginal RAW filename with extension, e.g. IMG_1234.CR3; the extension selects the decoder. Defaults to the attachment's own name.upload.raw
image_filenameNoOriginal JPEG filename with extension. Defaults to the attachment's own name.upload.jpg
raw_object_keyNoObject key returned by create_verification_upload for the RAW file.
image_object_keyNoObject key returned by create_verification_upload for the JPEG.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / image_file
      Added value: +{
+  "default": null,
+  "description": "The JPEG/PNG export of the same shot the user attached; pairs with raw_file.",
+  "properties": {
+    "download_url": {
+      "description": "URL the file can be downloaded from.",
+      "type": "string"
+    },
+    "file_id": {
+      "description": "The client's identifier for the file.",
+      "type": "string"
+    },
+    "file_name": {
+      "description": "Original file name, when known.",
+      "type": "string"
+    },
+    "mime_type": {
+      "description": "MIME type, when known.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "download_url",
+    "file_id"
+  ],
+  "type": "object"
+}
    • changedInput schema / properties / image_filename / description
      Previous value: -"Original JPEG filename with extension."New value: +"Original JPEG filename with extension. Defaults to the attachment's own name."
    • addedInput schema / properties / raw_file
      Added value: +{
+  "default": null,
+  "description": "The camera RAW file the user attached (.CR2/.CR3/.NEF/.ARW/.RAF/.ORF/.DNG ...); its file_name selects the decoder.",
+  "properties": {
+    "download_url": {
+      "description": "URL the file can be downloaded from.",
+      "type": "string"
+    },
+    "file_id": {
+      "description": "The client's identifier for the file.",
+      "type": "string"
+    },
+    "file_name": {
+      "description": "Original file name, when known.",
+      "type": "string"
+    },
+    "mime_type": {
+      "description": "MIME type, when known.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "download_url",
+    "file_id"
+  ],
+  "type": "object"
+}
    • changedInput schema / properties / raw_filename / description
      Previous value: -"Original RAW filename with extension, e.g. IMG_1234.CR3; the extension selects the decoder."New value: +"Original RAW filename with extension, e.g. IMG_1234.CR3; the extension selects the decoder. Defaults to the attachment's own name."
  2. Changed6 schema fields changed
    • addedInput schema / properties / image_base64 / description
      Added value: +"The JPEG export of the same shot as base64; pairs with raw_base64."
    • addedInput schema / properties / image_filename / description
      Added value: +"Original JPEG filename with extension."
    • addedInput schema / properties / image_object_key / description
      Added value: +"Object key returned by create_verification_upload for the JPEG."
    • addedInput schema / properties / raw_base64 / description
      Added value: +"The camera RAW file as base64, for files up to a few MB. For larger files call create_verification_upload and pass raw_object_key instead."
    • addedInput schema / properties / raw_filename / description
      Added value: +"Original RAW filename with extension, e.g. IMG_1234.CR3; the extension selects the decoder."
    • addedInput schema / properties / raw_object_key / description
      Added value: +"Object key returned by create_verification_upload for the RAW file."
  3. Changed1 schema field changed
    • removedInput schema / properties / anonymous_user_id
      Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "title": "Anonymous User Id"
-}
  4. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations, it discloses key behavioral traits: the tool returns a verification id immediately, runs analysis in the background for about a minute to 10+ minutes, and requires polling get_verification until completion. It also transparently states that calls count against a monthly quota, with free tier at 5/month. No contradiction with the annotations.

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?

The description is dense but efficient: purpose and exclusions first, then input routing, then async behavior and quota impact. Every sentence carries operational value, with no filler or repetition of schema details.

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

Completeness5/5

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

For an 8-parameter asynchronous tool, the description covers all essential operational aspects: when to use, what inputs to provide, how to route large files, how to retrieve the result, and cost/quota implications. An output schema exists, so the description does not need to explain return values.

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

Parameters5/5

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

Although schema coverage is 100%, the description adds strategic meaning by grouping parameters into three clear input modes: attachments (raw_file/image_file), inline base64 for small files, and object keys from create_verification_upload for large files. It also clarifies pairing requirements and size thresholds that the raw schema alone does not convey at a decision level.

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 a specific verb and resource: 'Verify a photo's authenticity from a RAW camera file and its JPEG export.' It also scopes the tool to requests for proof or genuineness checks and explicitly excludes feedback on the photo itself, making its role unmistakable.

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?

The description clearly states when to use the tool ('when the user asks for proof or a check that the photo is a genuine camera capture') and when not to use it ('not for feedback on the photo itself'). It also gives concrete input-mode guidance, including when to call create_verification_upload for large files. It does not explicitly contrast sibling verify_content_credentials, though the RAW+JPEG pairing makes the intended use clear.

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

All Lumethic Photo Verification 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