Skip to main content
Glama

vøiddo utilities

KDP puzzle book maker

kdp_puzzle_book
Read-onlyIdempotent

A ready-to-upload KDP paperback puzzle book: interior PDF, wrap cover, signed file check, previews and listing notes. Cost: 500 credits per call. Output: a file (application/zip) returned inline, at most 1 MiB. ZIP: interior.pdf, cover.pdf, check-report.pdf/.json, preview/*.png, listing.txt, README.txt

Input Schema

NameRequiredDescriptionDefault
mixNoVariety books only: the kinds of puzzle, in book order (default: wordsearch, sudoku, cryptogram, maze). Kids kinds only (kidssudoku, kidswordsearch, kidsmaze) make an activity book for kids; they do not mix with the others. Levels easy, medium or hard.
kindYessudoku, wordsearch, maze, cryptogram, wordscramble, numbersearch, kakuro, fillin, killersudoku, calcudoku, futoshiki, nonogram, skyscrapers, logicgrid, crossword, numberfill, samuraisudoku, jigsawsudoku, kidssudoku (sudoku for kids), kidswordsearch (word search for kids) or kidsmaze (mazes for kids); variety for a book of several kinds (see mix)
seedNoRebuild an earlier book exactly; omit for a new one
trimNo8.5x11
countYesNumber of puzzles. The fewest allowed fill KDP's 24-page minimum; the most are 400 sudoku (300 at hard or expert), 150 word searches, 200 mazes, 300 cryptograms, 55 word scrambles (40 at easy or hard), 150 number searches, 150 kakuro (100 at hard), 150 fill ins, 150 killer sudoku (120 at hard), 150 calcudoku, 200 futoshiki, 120 nonograms (no picture twice), 200 skyscrapers, 100 logic grids, 100 crosswords (no answer twice), 150 number fill ins, 150 samurai sudoku (75 at hard), 300 jigsaw sudoku (200 at hard), 300 sudoku for kids, 100 word searches for kids, 200 mazes for kids, 150 puzzles in a variety book (shared evenly by its kinds, at least 4 of each, none past its own maximum)
levelYeseasy, medium, hard (and expert for sudoku and mazes). For kidssudoku the level picks the grid: easy 4x4, medium 6x6, hard 9x9, mixed all three in that order. For kidswordsearch it picks the grid and the word count: easy 8x8 with 8 words across and down, medium 10x10 with 10, hard 12x12 with 12 in all eight directions. For kidsmaze it picks the size in squares: easy 6x7, medium 8x10, hard 11x13, mixed all three in that order
paperNowhite
titleNo
authorNo
themesNoWord search, word scramble, fill in or crossword themes to use, in order (default: the everyday themes, shuffled; the Christmas and winter ones only by name)
subtitleNo
cover_colorNoThe cover's color, so a series can look like no one else's. Default: the kind's own (sudoku navy, word search forest, maze terracotta, ...).
large_printNoEvery text read while solving at 16 pt or more. Nonograms need room: in large print, easy on 7x10 or larger and medium on 8.5x11 or 8.27x11.69 (no hard); in regular print, hard on 7x10 or larger. Logic grids: in large print (a spread a puzzle), easy on 7x10 or larger, medium and hard on 8x10 or larger; in regular print, hard on 7x10 or larger. Crosswords in large print (a spread a puzzle) on 7x10 or larger. Samurai sudoku in large print on 8.5x11 or 8.27x11.69, in regular print on 7x10 or larger
cover_layoutNoWhere the title sits on the front cover: puzzle_top (default: a puzzle from the book above the title), title_top (the title above the puzzle) or title_card (the puzzle across the whole front, the title on a card).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Beyond the readOnly/idempotent/non-destructive annotations, the description discloses two facts an agent cannot get from structured fields: a 500-credit cost per call and an inline 1 MiB output ceiling with the exact ZIP inventory. It does not say how long generation takes, whether credits are refunded on failure, or what 'signed file check' verifies, which keeps it off a 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?

Front-loaded with the deliverable, then cost, then output shape and ZIP contents — dense, zero filler. The final ZIP inventory is a raw comma list that reads tersely and 'signed file check' is unexplained, so it is efficient but not maximally clear.

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 14-parameter generator with no output schema, the description covers the two things an agent most needs to decide and plan: cost and the returned artifact set, including size. It leaves out failure/refund behavior and whether trim/paper/large_print conflicts are validated, but the critical calling information is present.

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

Parameters3/5

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

Schema coverage is 64% and the description adds nothing about parameters — no hint that kind/count/level interact or that mix is required for the 'variety' kind. The undocumented params (trim, paper, title, author, subtitle) are self-evident name/format fields with enums or defaults, so the description does not need to compensate heavily; baseline 3 applies.

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 names a concrete deliverable — a ready-to-upload KDP paperback puzzle book — and enumerates its artifacts (interior PDF, wrap cover, check report, previews, listing notes), which clearly separates it from kdp_preflight, kdp_report and kdp_spine_calc. It stops short of an explicit 'use this to generate X' verb phrase, and never names the sibling tools it is distinct from.

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

Usage Guidelines3/5

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

Usage is only implied: the phrase 'ready-to-upload KDP paperback puzzle book' positions it as the end-to-end generation step in the KDP pipeline, and the 500-credit price signals a call to make sparingly. There is no explicit when-to-use, when-not, or pointer to kdp_preflight/kdp_report for the verification path.

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