Skip to main content
Glama

GiftsToPrint

by com.giftstoprint
OverviewDiscussionsAdmin

Upload the photo for the poster

upload_photo

Store the photo that will be printed on the poster, and return the photo_url to pass to create_poster_checkout. Only use a photo the user has given in THIS conversation. Never reuse a photo or link from memory or an earlier conversation, and never use a product or poster image. If the user hasn't given a photo yet, ask them for one instead of calling this. Give exactly one of: photo (a file the user attached in this chat), image_url (a public https link to the image), image_base64, or upload_id (from get_photo_upload_link, once the user says they've uploaded). If you can't send the user's photo any of these ways, call get_photo_upload_link instead of asking the user for a link. JPEG, PNG or WebP, up to 20MB. Photos are kept for 12 months so the poster can be made and revised, then deleted automatically.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
photoNoA photo the user attached in this chat (ChatGPT file reference).
image_urlNoPublic https:// address of the image.
upload_idNoThe upload_id from get_photo_upload_link, after the user has uploaded on that page.
image_base64NoThe image file encoded as base64 (a data: URL prefix is fine).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / $defs
      Added value: +{
+  "OpenAIFile": {
+    "additionalProperties": false,
+    "properties": {
+      "download_url": {
+        "type": "string"
+      },
+      "file_id": {
+        "type": "string"
+      },
+      "file_name": {
+        "type": "string"
+      },
+      "mime_type": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "download_url",
+      "file_id"
+    ],
+    "type": "object"
+  }
+}
    • addedInput schema / properties / photo
      Added value: +{
+  "$ref": "#/$defs/OpenAIFile",
+  "description": "A photo the user attached in this chat (ChatGPT file reference)."
+}
    • addedInput schema / properties / upload_id
      Added value: +{
+  "description": "The upload_id from get_photo_upload_link, after the user has uploaded on that page.",
+  "pattern": "^[0-9a-f]{32}$",
+  "type": "string"
+}
  2. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations only declare the write/open-world/non-idempotent profile; the description supplies the operational detail beyond that — accepted formats (JPEG/PNG/WebP), 20MB cap, and the 12-month retention/deletion policy. That data-lifecycle disclosure is exactly what annotations cannot convey.

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?

Opens with what it does and the return value, then layers constraints and the fallback path. Every sentence carries a distinct rule (source restriction, exclusivity, format limits, retention); nothing is padding.

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?

No output schema exists, yet the description states the return value (photo_url) and which sibling consumes it, closes the input-exclusivity question, and covers the no-photo-pending branch. Nothing an agent needs to call this correctly is missing.

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 genuinely new constraint the schema cannot express: exactly one of photo/image_url/image_base64/upload_id, plus the precondition that upload_id must come from get_photo_upload_link after the user uploads. It does not restate the per-parameter meanings, which the schema already covers.

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?

States a specific verb and resource ('Store the photo that will be printed on the poster') and explicitly names the downstream sibling create_poster_checkout as the consumer of the returned photo_url. An agent can separate this from get_photo_upload_link and the other poster tools without inspecting schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use, when-not-to-use, and an alternative: only photos from THIS conversation, never reuse from memory or earlier chats, never product/poster images, ask the user instead if no photo, and call get_photo_upload_link when the photo can't be sent directly. This is a full routing decision tree.

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

All GiftsToPrint 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