ChartAnt

Dashboard image

generate_dashboard

Read-onlyIdempotent

Combine KPI cards, charts, maps and short notes into ONE image, in rows (1-4 rows, 1-4 panels per row, at most 8 panels). For weekly email updates, Slack posts, client reports and slides. Each panel is a chart definition with its 'type' (kpi, line, column, bar, pie, area, country-map, world-map, county-map, small-multiples, or note for a sentence of text: {type:'note', text}). Typical: a row of KPI cards, then a trend chart beside a map or a top-10 bar chart, then a note with the takeaway. For a multi-page document with text use create_report instead. 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": {
      "rows": "<rows>"
    },
    "name": "generate_dashboard"
  }
}

Input Schema

Name	Required	Description
`rows`	Yes	Rows of panels, top to bottom; each panel like {"type":"line","title":"…","data":[…]}.
`title`	No	Heading at the top of the image.
`width`	No	Image width in pixels (default 1200).
`subtitle`	No	Line under the heading, e.g. 'Week 12'.
`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).

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 15, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already cover safety (readOnlyHint, idempotentHint, non-destructive, closed-world), and the description adds the return payload: hosted PNG link, share page, alt text, editable PowerPoint/Excel links. It does not mention limits (data size, panel payload constraints) beyond the count caps, so it is strong but not exhaustive.

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 core action and limits, then use cases, then panel types, then a typical layout, then the sibling exclusion, then returns. Dense with no filler, though the 'Typical:' sentence and the return list make it longer than strictly minimal.

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 correctly spends its ending on return values, and it compensates for the loosely typed 'rows' schema by listing panel types and the note syntax. Minor gaps remain around panel data shape and any payload limits, but an agent has enough to call it correctly.

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 would be 3, but the description goes beyond the schema by enumerating valid panel types (kpi, line, column, bar, pie, area, country-map, world-map, county-map, small-multiples, note) and the note payload syntax {type:'note', text}. That matters because the schema types 'rows' items only as an open object; the data field format remains unstated.

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?

States a specific verb and output ('Combine KPI cards, charts, maps and short notes into ONE image') plus the composition constraint (1-4 rows, 1-4 panels per row, max 8). This clearly separates it from the single-chart siblings like generate_line_chart and from create_report.

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?

Gives concrete usage contexts (weekly email updates, Slack posts, client reports, slides) and an explicit exclusion with routing: 'For a multi-page document with text use create_report instead.' An agent can decide between the composite-image tool and the document tool without inference.

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.