ChartAnt

More chart types

generate_more_charts

Read-onlyIdempotent

Draw one of these chart types and get an image link. Set type and data as below. rose (Nightingale/polar area), radial-bar: data [{category, value}]. lollipop: data [{category, value}]. dumbbell (before/after per row): data [{category, start, end}], optional startLabel, endLabel. slope (change between two points): data [{category, before, after}], optional beforeLabel, afterLabel. bubble: data [{x, y, size, label?, group?}], optional axisXTitle, axisYTitle. chord (flows between groups): data [{source, target, value}]. circle-packing: data [{name, value, group?}]. parallel-coordinates (compare items on several measures): data [{name, : number, ...}], at least two numeric measures. tree (hierarchy): data {name, children: [{name, children: [...]}]}. population-pyramid: data [{age, group, value}] with exactly two groups (e.g. Men, Women). marimekko (100% stacked with variable widths): data [{category, group, value}]. sunburst (hierarchy as rings), icicle (hierarchy as bands): data {name, children: [{name, value} or {name, children}]}; innermost items need a value. beeswarm (every value as a dot, no overlap): data [{value, group?, label?}], optional axisXTitle. density (smoothed distribution curves): data [{value, group?}], at least 3 values, optional axisXTitle. Use the dedicated generate_* tool for common types (line, column, pie, maps…). Returns a hosted PNG link, a share page, alt text and editable PowerPoint/Excel links.

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": {
      "type": "<type>",
      "data": "<data>"
    },
    "name": "generate_more_charts"
  }
}

Input Schema

Name	Required	Description
`data`	Yes	Rows (or a tree object for tree, sunburst and icicle) in the format listed for the type.
`type`	Yes	Which chart to draw; see the description for each type's data format.
`theme`	No	default (light) or dark background.
`title`	No	Title shown above the chart.
`width`	No	Image width in pixels (default 720).
`height`	No	Image height in pixels (default 480).
`endLabel`	No	dumbbell: name of the end value, e.g. '2025'.
`afterLabel`	No	slope: name of the right column, e.g. 'After'.
`axisXTitle`	No	bubble, beeswarm, density: x-axis title.
`axisYTitle`	No	bubble: y-axis title.
`brandTheme`	No	Name of a brand theme saved on the user's account (their colours and footer), only when the user asks for their theme. Or "colorblind" for colours that people with colour-vision deficiency can tell apart (anyone can use it).
`startLabel`	No	dumbbell: name of the start value, e.g. '2020'.
`beforeLabel`	No	slope: name of the left column, e.g. 'Before'.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 15, 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, closed-world behaviour. The description adds what annotations cannot: the return payload (hosted PNG link, share page, alt text, editable PowerPoint/Excel links), which matters since there is no output schema. No cost/rate-limit or failure-mode detail, so not 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-loaded with the action and the return value, then a dense type→data-format catalogue with zero filler sentences. The semicolon-separated run-on is harder to scan than bullets would be, but every clause carries a real schema constraint.

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?

For a 16-type, 13-parameter generator with no output schema, all the decision-critical information is present: which types exist, the data contract for each, when to use a sibling instead, and what comes back. Remaining parameters (theme, width, height, labels) are fully described in the schema itself.

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 baseline is 3, but the description goes beyond the schema by spelling out the exact data shape required per type (e.g. dumbbell needs {category, start, end}; population-pyramid needs exactly two groups; density needs at least 3 values) — detail the schema only gestures at with "in the format listed for the type". This is genuinely load-bearing constraint information.

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?

Specific verb+resource ("Draw one of these chart types and get an image link") plus an explicit roster of the 16 supported types with a one-line semantic gloss for each (rose = Nightingale/polar area, dumbbell = before/after per row). It also distinguishes itself from siblings by pointing to the dedicated generate_* tools for common types.

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?

Explicit routing rule: "Use the dedicated generate_* tool for common types (line, column, pie, maps…)", which tells the agent when NOT to use this tool. The per-type parentheticals also help pick the right type. It stops short of stating exclusions among the 16 types themselves (e.g. slot/circle-packing vs. treemap), so not a 5.

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

All ChartAnt 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.