Zovo Cross Sum Puzzles

Generate cross sum puzzles

generate_cross_sums

Read-onlyIdempotent

Use this when the user wants printable cross-sum puzzles (cross sums, number crossword puzzles with sums, addition logic puzzles) as a PDF with an answer key, or wants to solve one on screen. Each grid from 6 x 6 to 12 x 12 (counting the clue row and column) has white squares for the digits 1 to 9 and clue squares with sums; each run of white squares adds up to its clue with no repeated digit. Put one object per puzzle in puzzles[] when they differ (size, difficulty, seed); for a set of the same kind, set count with size and difficulty. A solver checks each puzzle for one solution. The PDF has 1, 2 or 4 puzzles per page on Letter or A4, an optional title and name line, and answer pages; the card lets the user fill in digits and check them. Defaults: 1 medium 8 x 8 puzzle, Letter, 1 per page, name line and answer key on. Does not solve a puzzle from a photo or make grids larger than 12 x 12.

Input Schema

Name	Required	Description
`seed`	No	Starting seed; puzzle N uses seed + N - 1. Reuse it to reprint the same puzzles. Example: 2026
`size`	No	Grid size for all puzzles, 6 to 12 (default 8), counting the clue row and column. Example: 10
`count`	No	How many puzzles when they are all the same kind (1 to 12, default 1). Example: 4
`paper`	No	letter (default, US 8.5 x 11 in) or a4. Example: a4
`title`	No	Title printed at the top of each page. Example: Weekend Cross Sums
`puzzles`	No	One object per puzzle when the puzzles differ, e.g. [{"size":6,"difficulty":"easy"},{"size":10,"difficulty":"hard"}]. Leave out and use count for a set of the same kind. Up to 12.
`per_page`	No	Puzzles per printed page: 1 (default), 2 or 4. Example: 2
`name_line`	No	Print a Name and Date line on the puzzle pages (default true). Example: false
`answer_key`	No	Add answer pages with the solved grids (default true). Example: true
`difficulty`	No	Difficulty for all puzzles: easy, medium (default) or hard. Example: easy

Output Schema

Name	Required	Description	Default
`count`	Yes
`notes`	Yes
`pages`	Yes
`paper`	Yes
`title`	Yes
`puzzles`	Yes
`per_page`	Yes
`downloads`	Yes
`name_line`	Yes
`answer_key`	Yes
`puzzle_count`	No
`all_one_solution`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 8, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already declare safe read-only, idempotent, closed-world behavior, and the description adds substantial context: a solver checks each puzzle for one solution, PDF layout options include page counts and answer pages, and the on-screen card is interactive. It also discloses defaults and the mutually exclusive batch modes.

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?

The description is front-loaded with the usage trigger and keeps every sentence relevant, but it is a single dense paragraph. It could be slightly easier to scan if the defaults and batch-mode distinction were separated, though the content is appropriately sized for a 10-parameter generative tool.

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?

Given the tool's complexity, 10 optional parameters, and an output schema, the description covers the essential modes, constraints, defaults, and behavioral outcomes. Nothing an agent needs in order to choose or invoke the tool correctly appears to be 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 schema already documents each parameter with examples and defaults. The description adds relational semantics beyond the schema by explaining that puzzles[] should be used when puzzles differ, while count applies to a set of the same kind, and it summarizes the default configuration.

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 names a specific verb and resource: generating cross-sum puzzles, with synonyms (number crossword puzzles with sums, addition logic puzzles) and both printable PDF and on-screen card outputs. An agent can immediately tell what the tool produces and in which formats.

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?

It explicitly states when to use the tool ('when the user wants printable cross-sum puzzles... or wants to solve one on screen') and gives exclusions ('Does not solve a puzzle from a photo or make grids larger than 12 x 12'). It also clarifies when to use puzzles[] versus count for batches.

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

All Zovo Cross Sum Puzzles 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?