Original solver-checked number puzzles as JSON or printable SVG, plus a daily puzzle.
Scored across 1 tool
There is only a single tool, so there is no possibility of overlap or misselection; its purpose (generate a number puzzle with rules, JSON, SVG URL and optional solution) is unambiguous.
The lone name get_number_puzzle follows a clean verb_noun snake_case convention that clearly signals what it does and the resource it acts on.
A one-tool surface is thin by general standards, but the server has a deliberately narrow single-purpose scope (puzzle generation), so one well-designed tool is a defensible fit.
The tool covers the core lifecycle of its domain: generating a puzzle with rules, structured JSON, a printable SVG and an optional solution across three puzzle families and three difficulties. Only minor gaps exist, such as no lookup of a previously generated puzzle by ID or a category/difficulty enumeration.
Returns an original number puzzle (Target, Cage Grid or Brick Pyramid) at easy, medium or hard, with its rules, the puzzle as JSON, an SVG image URL for printing and, optionally, the solution. Cage Grids and Pyramids have exactly one solution (solver-checked). Use it for math practice, classroom warm-ups, puzzle apps or a daily puzzle. Free tier 50 puzzles a day without a key; paid API keys (Bearer) for more.
| Name | Required | Description | Default |
|---|---|---|---|
| seed | No | Any text; the same type + level + seed always returns the same puzzle. Omit for a random one. | |
| type | No | target = reach a number with + - x /; cage = Latin-square cage grid (4x4 easy, 5x5 medium, 6x6 hard); pyramid = brick pyramid of sums | cage |
| daily | No | true = today's puzzle (same for everyone, changes at 00:00 UTC) | |
| level | No | easy | |
| include_solution | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/idempotent/non-destructive/non-open-world, so the safety profile is covered. The description adds genuinely useful context beyond them: determinism via seed, daily puzzles rotating at 00:00 UTC, the 50/day free tier, and Bearer-key auth for higher volume. It does not describe response size or pagination, but for a read-only generator that is minor.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Four sentences, front-loaded with what is returned and the guarantee of a unique solution before moving to use cases and pricing. Dense but every sentence carries information; the type/level enumeration is slightly redundant with the enum descriptions.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, so the description must (and does) enumerate the return payload: rules, puzzle JSON, SVG URL, and optional solution, plus the unique-solution guarantee for cage/pyramid. Coverage of params is adequate given 60% schema coverage; only response shape details (e.g., field names) are left to the caller to discover.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 60%, and the two most important params (seed, type) are already well documented in the schema. The description restates the puzzle types and difficulty levels and implies include_solution ('optionally, the solution') but adds no format or syntax detail beyond what the schema provides. Baseline 3 fits.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a concrete verb+resource (returns an original number puzzle) and enumerates the three puzzle types and three difficulty levels. The return payload — rules, puzzle JSON, SVG print URL, optional solution — is spelled out, so an agent knows exactly what comes back without opening a schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives explicit usage contexts ('math practice, classroom warm-ups, puzzle apps or a daily puzzle') and notes the free-tier vs paid-key split, so the agent knows the intended domain. There are no sibling tools, so no alternative-routing guidance is needed, but it stops short of stating when NOT to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_number_puzzleDeterministic Sudoku puzzles, progress checks, logical hints, and step-by-step solutions.
Deterministic procedural SVG/PNG backgrounds: 58 generators, curated palettes, brand kits.
Play six arcade puzzles, submit verified AI scores, and explore public leaderboards.
15 tools for chess variant analysis, hex map generation, and board game utilities
Add one secure layer between your agents and this server.
