Oh, my Dots!

create_crossword

Create a crossword puzzle URL. You must provide the list of words and hints. The list must have between 3 and 30 pairs words/hints. If user specifies count/topic, generate appropriate words and hints first, then call this tool with the words parameter.

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": {
      "words": "<words>"
    },
    "name": "create_crossword"
  }
}

Input Schema

Name	Required	Description
`topic`	No	Optional: Topic/theme for the crossword. Only for reference.
`words`	Yes	Words with hints in format "word: hint", separated by newlines. Must contain 3-30 lines. Each word must be 3-20 letters long. Non-alphabetic characters except colon are allowed. Non-alphabetic characters do not count towards length. Words do not need to be uppercased. Keep hints brief, long hints take up too much space on the board.
`language`	No	Optional: Language for the crossword. Use the same language as the prompt. Please use ISO 639-1 codes: en, es, fr, de, pt.
`word_count`	No	Optional: Number of words requested (3-30). Only for reference/validation.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 4, 2026

TDQS

A3.6/5.0

Behavior3/5

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

No annotations exist, so the description carries the burden. It usefully discloses that the output is a URL and that the words list must be 3-30 pairs, but says nothing about authentication, rate limits, persistence, or whether anything is stored server-side.

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?

Three short sentences, front-loaded with the purpose before the input requirement and the generation workflow. No filler, though the ordering could surface the required-words constraint slightly earlier.

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?

With no output schema, the description compensates by stating the return value is a URL, and it covers the required input and its cardinality. It is nearly complete for a 4-param creation tool, missing only edge-case or error behavior.

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 description coverage is 100%, so the schema already documents format, length limits, and language codes. The description adds only the mandate to supply words and hints, which is already implied by the required parameter; baseline 3 is appropriate.

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 specific verb and resource ('Create a crossword puzzle URL') so the agent knows exactly what is produced. It is clearly distinguishable from siblings like create_cryptogram and create_word_search, but it never explicitly contrasts itself with them.

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 concrete usage workflow: when the user specifies count/topic, generate words and hints first, then call this tool with the words parameter. This is clear actionable context, though it offers no explicit exclusions or alternatives against the sibling tools.

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

All Oh, my Dots! 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?