Zovo Word Cloud

Make word cloud

make_word_cloud

Read-onlyIdempotent

Use this when the user wants a word cloud, word art or tag cloud from text (survey answers, reviews, an article, notes) or from a list of words with weights, for example "make a word cloud of these comments". Takes text (up to 100,000 characters) or up to 500 word and weight pairs, plus max words (10 to 200), stop-word language (en, es, fr, de, it, pt or none), case rule, shape (rectangle or circle), orientation, colour set, font sizes and a seed. Returns the top words with counts, words left out and why, layout and PDF text checks, an interactive view, and SVG, PDF and CSV downloads. Does not read files or web pages, does not split Chinese, Japanese or Thai text into words, and does not stem or group words by meaning.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "make_word_cloud"
  }
}

Input Schema

Name	Required	Description
`case`	No	fold (default for text): Apple and apple count as one word, shown in lower case; as_written (default for a word list): case is kept and counted apart.
`seed`	No	Layout seed, 0 to 999999 (default 1). The same input and seed give the same layout; another seed gives another arrangement.
`text`	No	Text to turn into a cloud, up to 100,000 characters, e.g. survey answers. Give text or words, not both.
`shape`	No	rectangle (default, 720 x 520 pt) or circle (520 pt across).
`title`	No	Optional title printed above the cloud and used in file names, up to 80 characters, e.g. "Customer feedback, Q3".
`words`	No	Alternative to text: up to 500 words with weights, e.g. [{"word":"growth","weight":12},{"word":"New York","weight":5}]. Each word up to 40 characters; weights above 0.
`palette`	No	Colour set: classic (default), ocean (blues), forest (greens), sunset (reds and oranges) or mono (greys).
`max_words`	No	Most words to draw, 10 to 200 (default 100), e.g. 50. The highest counts are drawn.
`page_size`	No	PDF page, landscape: letter (default) or a4.
`min_length`	No	Shortest word to count, in characters, 1 to 20 (default 2), e.g. 3.
`stop_words`	No	Stop-word list to remove common function words: en (default, English), es, fr, de, it, pt, or none to keep all words. Other languages keep all words, e.g. "es".
`orientation`	No	horizontal (default): words read left to right; mixed: about a third of the words read bottom to top.
`exclude_words`	No	Extra words to leave out, up to 100, matched without case, e.g. ["project", "team"].
`max_font_size`	No	Largest font size in points, up to 120 (default 64), at least min_font_size, e.g. 72.
`min_font_size`	No	Smallest font size in points, 8 to 40 (default 10), e.g. 12.
`include_numbers`	No	Count number-only words such as 2026 (default false).

Output Schema

Name	Required	Description	Default
`rules`	Yes
`title`	Yes
`counts`	No
`source`	Yes
`left_out`	Yes
`settings`	Yes
`warnings`	Yes
`downloads`	Yes
`top_words`	Yes
`layout_check`	Yes
`deterministic`	Yes
`preview_count`	No
`left_out_count`	Yes
`pdf_text_check`	Yes
`words_in_cloud`	Yes
`largest_font_pt`	Yes
`not_in_top_count`	Yes
`smallest_font_pt`	Yes
`words_considered`	Yes
`font_scale_percent`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 8, 2026

TDQS

A4.1/5.0

Behavior5/5

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

Annotations cover safety (readOnly, idempotent, non-destructive, closed-world), and the description adds substantial context beyond them: input ceilings (100,000 characters, 500 word/weight pairs), seed-driven layout reproducibility, and a detailed account of the return payload (top words with counts, omitted words and reasons, layout/PDF text checks, interactive view, SVG/PDF/CSV downloads). The explicit language-coverage and no-stemming caveats are exactly the behavioral limits an agent needs before promising an output.

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 use case, then a compact inventory of knobs, then hard limits — a sensible order for a 16-parameter tool. The middle sentence is long and list-like, but given the parameter count the density is largely earned.

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 and rich annotations already present, the description only needs to frame inputs, limits and caveats, and it does all three. An agent could invoke this correctly without opening another tool definition, aside from the unresolved choice against count_words.

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% and each parameter already carries defaults, ranges and examples, so the schema does the heavy lifting. The description's prose summary of max words, stop-word languages, case rule, shape, orientation, palette, font sizes and seed restates rather than extends that information, so the 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?

States a concrete verb and artifact ('make a word cloud, word art or tag cloud') and enumerates the input sources it accepts (survey answers, reviews, an article, notes, weighted word lists), so the agent knows exactly what it produces. It stops short of naming the sibling count_words, so the routing between counting vs. visualizing is left to inference.

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?

Opens with an explicit trigger ('Use this when the user wants a word cloud...') plus an example user utterance, which is strong when-to-use guidance. It also gives negative boundaries ('does not read files or web pages', 'does not split Chinese, Japanese or Thai', 'does not stem'), but never names count_words as the alternative for plain frequency questions.

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

All Zovo Word Cloud 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?