Skip to main content
Glama

Make a photo book

create_book
Idempotent

Use this when the person wants a photo book (Dutch: fotoboek) made from photos they attached, direct image links, or a public iCloud Shared Album link. Designs a draft book from the photos in the supplied order; nothing is ordered or charged. Photos the person attached in this chat go in attachments, which ChatGPT fills in; never pass local file paths. Otherwise provide direct CDN image URLs or uploadIds from POST /api/connector/photos in photos (you can choose the best photos yourself and send only those, in order; HEIC and rotated phone photos are accepted), or a public iCloud Shared Album link as sharedAlbumUrl (https://www.icloud.com/sharedalbum/#TOKEN). A book needs at least 24 pages to be printed, so a handful of photos gives a book that can be viewed but not yet ordered. Returns a preview and a private link to save the book by email. No account setup. Allow up to 180 seconds for imports.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "idempotencyKey": "<idempotencyKey>",
      "title": "<title>"
    },
    "name": "create_book"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleYes
photosNoPublic https image URLs on a known CDN, or uploadIds. Not for chat attachments or local paths.
languageNoTwo-letter code of the language the person writes in, such as nl or en.
productIdNo
attachmentsNoPhotos the person attached in this chat. ChatGPT supplies the file objects; never invent them.
idempotencyKeyYes
sharedAlbumUrlNoPublic iCloud Shared Album link, used instead of photos.

Output Schema

NameRequiredDescriptionDefault
albumNo
titleNo
bookIdNo
statusNo"ready", or "processing_or_interrupted" while the same request is still running.
editUrlNo
messageNo
claimUrlNoPrivate link where the person saves the book with their email, then edits and orders it.
languageNoThe chat's language, as passed in.
bookTokenNoPrivate token for get_book. Keep it private.
orderableNoWhether the book can be printed as it is.
photoCountNo
previewUrlNo
operationIdNo
unavailableReasonNoWhy it cannot be printed yet, such as too few pages.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Goes well past the annotations by disclosing that this only builds a draft (no ordering or charging), that a book needs at least 24 pages to be printable, that no account setup is required, that imports can take up to 180 seconds, and that the response includes a preview plus a private save-by-email link. These are exactly the operational facts an agent needs that readOnlyHint/destructiveHint do not convey.

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?

Front-loaded with the trigger, then input mechanics, then constraints and return behavior — a sensible order. It is dense and long, but nearly every clause (page minimum, 180s timeout, no local paths) carries information the agent would otherwise get wrong.

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 a 7-parameter creation tool with an output schema, the description covers inputs, side effects, timing, and output artifacts well enough to call it correctly on the first attempt. The remaining undocumented fields are low-risk identifiers rather than decision-critical inputs.

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?

Adds real meaning beyond the 57%-covered schema: it explains the two mutually exclusive photo channels, warns never to pass local file paths for attachments (ChatGPT fills them in), names the source endpoint for uploadIds, notes that the agent may select and order the best photos, and confirms HEIC/rotated phone photos are accepted. It leaves productId and idempotencyKey unexplained, but those are minor required/optional plumbing.

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?

States a concrete verb and resource ('Designs a draft book from the photos in the supplied order') and immediately bounds the outcome with 'nothing is ordered or charged'. It does not, however, distinguish itself from the sibling start_photo_book, which an agent could reasonably confuse with this draft-creation step.

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?

Gives a clear triggering condition ('Use this when the person wants a photo book ... made from photos they attached, direct image links, or a public iCloud Shared Album link') and tells the agent which input channel to pick in each case. There is no explicit exclusion or pointer to compare_photo_book_prices / start_photo_book / create_checkout for the next step.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources