Printablesmith

Crossword

make_crossword

Read-onlyIdempotent

Make a printable crossword puzzle with clues and an answer key, laid out automatically so the answers cross. Write a short clue suited to the solver for each answer (one that does not contain the answer); an answer without a clue gets the site’s own checked clue when it has one. 2 to 30 answers of 2 to 21 letters each; 10 to 18 cross best. Children can also solve it on a screen.

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": {
      "clues": "<clues>"
    },
    "name": "make_crossword"
  }
}

Input Schema

Name	Required	Description
`seed`	No	Which random version to make. Leave out for a fresh one; pass the seed from an earlier result to keep that version while changing other settings.
`clues`	Yes	The answers and their clues.
`large`	No	Bigger clues and squares for young children and beginning readers (for older eyes, use large_print).
`paper`	No	Paper size: letter (US Letter, the default; US and Canada) or a4 (everywhere else).
`title`	No	The title printed at the top of the sheet, e.g. "Solar System Crossword". Keep it short.
`word_bank`	No	Print the answers in a word bank, for easier solving.
`decoration`	No	A themed border with matching pictures, drawn around the sheet: "line" for a plain border, "none" for nothing, or a theme such as halloween, christmas, thanksgiving, spring, dinosaurs, space, ocean, animals, birthday, back-to-school (95 themes; find_printables shows a theme’s name). Leave out for no border.
`large_print`	No	Large print for older eyes or low vision: bigger, bolder letters and roomier layouts (sizes are capped to fit). For young children, use large.
`dyslexia_font`	No	Print in OpenDyslexic, a typeface some readers with dyslexia find easier.

Output Schema

Name	Required	Description
`url`	Yes	The sheet on printablesmith.com, every setting filled in: open it to adjust, download the PDF or print
`seed`	No	The seed that rebuilds this exact sheet
`maker`	Yes	Which maker drew it, e.g. wordSearch
`notes`	Yes	Things worth knowing about this sheet
`title`	Yes	The sheet title
`playUrl`	No	Where a child can solve it on a screen (word search, crossword, maze, sudoku)
`summary`	Yes	What the sheet is
`settings`	Yes	The address settings, as the maker reads them

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 11, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare read-only, idempotent, non-destructive, non-open-world behavior, and the description adds real depth on top: the seed's role in reproducing a prior version while changing settings, the fallback to the site's own checked clue when a clue is omitted, and layout caps. It doesn't discuss failure cases (e.g. what happens when answers can't interlock), which keeps it below 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-loads the core capability in the first clause, then packs constraints and audience notes into two dense but purposeful sentences. Every clause carries information; the child/on-screen remark at the end is the least essential but still informs output choice.

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?

With an output schema present, return values needn't be explained, and the description still covers the input contract, reproduction via seed, audience variants (large vs large_print, dyslexia font), decoration themes, and paper sizing. Nothing an agent needs to invoke it 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 meaning the schema doesn't: a clue must not contain its answer, clues are best under 60 characters, and the effective answer-length working range (2-21 letters, 10-18 ideal) is narrower than the schema's maxLength of 30. That guidance materially shapes how an agent fills the parameters.

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 (make a printable crossword puzzle) plus the defining output traits: clues, an answer key, and automatic interlocking layout. This clearly separates it from siblings like make_word_search or make_word_scramble without needing their schemas.

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 concrete operating guidance: write a clue per answer, the system supplies a checked clue if omitted, 2-30 answers of 2-21 letters, and '10 to 18 cross best' as the sweet spot. It lacks an explicit 'use X instead' routing statement to sibling puzzle makers, but the sizing and clue guidance makes correct usage inferable.

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

All Printablesmith 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?