ChartAnt

Report from several charts

create_report

Read-only

Put several charts, maps or KPI cards and some text into one report. Returns a link to a report page (shareable, PDF download) and a PowerPoint deck with a slide per chart. Each chart block takes the same fields as the render API, with its 'type' (e.g. column, line, pie, country-map, world-map, county-map, kpi).

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": {
      "title": "<title>",
      "blocks": "<blocks>"
    },
    "name": "create_report"
  }
}

Input Schema

Name	Required	Description
`title`	Yes
`blocks`	Yes	In order: headings, paragraphs and charts (at most 12 charts).
`subtitle`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 14, 2026

TDQS

A4.1/5.0

Behavior4/5

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

The annotations only give readOnlyHint=true, which is consistent with a non-destructive generator that produces a new artifact. The description then adds genuinely new behavioral detail: the output is a shareable report page with PDF download plus a PowerPoint deck with one slide per chart. It does not mention limits or whether the link persists or expires.

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 tight sentences, front-loaded with the purpose before the return values and the block format. The reference to 'the render API' is slightly under-specified since the agent may not know that API, but overall there is no wasted wording.

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 a sentence explaining what comes back. Nested block structure, ordering, and the 12-chart cap are already documented in the schema, so the remaining gap is minor: nothing about rate limits, persistence of the generated link, or failure modes.

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 only 33%, so the description has to carry weight, and it does for the most opaque parameter: the `chart` object is a free-form object in the schema, and the description explains it takes the render API fields with a `type` enum example set (column, line, pie, country-map, world-map, county-map, kpi). It adds nothing about `title` or `subtitle`, which the schema already constrains.

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?

Names a specific verb and resource (put several charts/maps/KPI cards plus text into one report) and states what is produced (a shareable report link and a PPTX deck). That scope distinguishes it from the single-chart `generate_*` siblings and from `generate_dashboard` without needing their schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the multi-block composition framing: use this when you want several charts plus prose in one deliverable. It never states exclusions or points at alternatives such as `generate_dashboard` or `create_living_chart`, so the agent must infer the boundary.

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.

Resources

Need Help?