Darwin-hosted AntV bar, column and line charts. Free rendering with bounded PNG outputs.
Scored across 3 tools
The three tools map to distinct chart types, and descriptions explicitly differentiate bar (horizontal) from column (vertical), including guidance on when to prefer column. The bar/column distinction still requires careful reading, but boundaries are stated clearly enough to avoid misselection.
All three tools follow the same generate_<chart_type>_chart pattern, making the set highly predictable. An agent can infer the naming scheme and extend it mentally to other chart types.
Three tools is on the low end but each earns its place with a specific chart type and shared rendering contract. The set is tightly scoped rather than padded, though it leaves little room for choice.
Coverage of the charting domain is notably partial: common types like pie, scatter, area, and stacked variants are absent, so many visualization requests will dead-end. The three provided types are fully self-contained (same input limits, PNG output), which limits the severity of the gap.
Generate a horizontal bar chart to show data for numerical comparisons among different categories, such as, comparing categorical data and for horizontal comparisons. Hosted by Darwin using AntV's public free renderer. Returns a PNG image. Accepts at most 50 rows with bounded image sizes. No API key is required; payments are not supported.
| Name | Required | Description | Default |
|---|---|---|---|
| data | Yes | ||
| group | No | Whether grouping is enabled. When enabled, bar charts require a 'group' field in the data. When `group` is true, `stack` should be false. | |
| stack | No | Whether stacking is enabled. When enabled, bar charts require a 'group' field in the data. When `stack` is true, `group` should be false. | |
| style | No | ||
| theme | No | Set the theme for the chart, optional, default is 'default'. | default |
| title | No | ||
| width | No | ||
| height | No | ||
| axisXTitle | No | ||
| axisYTitle | No |
| Name | Required | Description |
|---|---|---|
| artifact | Yes | |
| provenance | Yes | |
| requestMetadata | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, open-world, non-destructive behavior. The description adds useful operational context: PNG output, external Darwin/AntV rendering, 50-row limit, bounded image sizes, and no API key or payments.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with the core purpose and key constraints. Minor redundancy in "such as, comparing categorical data and for horizontal comparisons" keeps it from being maximally tight.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Output schema and annotations cover return values and safety profile, so those need not be in the description. However, with 10 parameters, nested style options, and low schema coverage, the description is too thin on parameter usage details for full completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is only 30% across 10 parameters. The description only indirectly mentions the 50-row data cap and bounded image sizes; it does not explain group/stack/style/theme/title/axis parameters or how they interact.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource: "Generate a horizontal bar chart." The horizontal orientation clearly distinguishes it from generate_column_chart, and the comparison purpose is explicit.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives clear usage context: numerical comparisons among categories and horizontal comparisons. It does not explicitly say when to choose generate_column_chart or generate_line_chart instead, but the intended use case is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate a column chart, which are best for comparing categorical data, such as, when values are close, column charts are preferable because our eyes are better at judging height than other visual elements like area or angles. Hosted by Darwin using AntV's public free renderer. Returns a PNG image. Accepts at most 50 rows with bounded image sizes. No API key is required; payments are not supported.
| Name | Required | Description | Default |
|---|---|---|---|
| data | Yes | ||
| group | No | Whether grouping is enabled. When enabled, column charts require a 'group' field in the data. When `group` is true, `stack` should be false. | |
| stack | No | Whether stacking is enabled. When enabled, column charts require a 'group' field in the data. When `stack` is true, `group` should be false. | |
| style | No | ||
| theme | No | Set the theme for the chart, optional, default is 'default'. | default |
| title | No | ||
| width | No | ||
| height | No | ||
| axisXTitle | No | ||
| axisYTitle | No |
| Name | Required | Description |
|---|---|---|
| artifact | Yes | |
| provenance | Yes | |
| requestMetadata | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, open-world, non-destructive, non-idempotent, but the description adds real context: the rendering host (Darwin/AntV), that the output is a PNG image, row and size bounds, and that no API key or payment is involved. It stops short of disclosing latency, rate limits, or failure behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The purpose and selection rationale are front-loaded, with operational constraints packed efficiently afterward. The clause about eyes judging height is wordy but earns its place by justifying tool choice over alternatives.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Hosting, auth, output type, and limits are covered, and the output schema means return values need no explanation. But for a 10-parameter tool with nested style and a mutually exclusive group/stack pair, the description provides no parameter-level guidance to supplement the thin schema coverage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is only 30% across 10 parameters, so the description must compensate and largely does not. It only restates limits already in the schema (50-row maximum, bounded image sizes) and says nothing about group/stack interplay, the nested style object, palette, theme, or axis titles.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ("Generate a column chart") and adds a usage rationale about comparing categorical data, which implicitly separates it from the line-chart sibling. It never names generate_bar_chart, so the column-vs-bar distinction an agent most needs is left implicit.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives a clear when-to-use condition: comparing categorical data, especially when values are close, because height is easier to judge than area or angles. There is no explicit when-not or named alternative, so an agent still has to infer bar vs. column vs. line selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate a line chart to show trends over time, such as, the ratio of Apple computer sales to Apple's profits changed from 2000 to 2016. Hosted by Darwin using AntV's public free renderer. Returns a PNG image. Accepts at most 50 rows with bounded image sizes. No API key is required; payments are not supported.
| Name | Required | Description | Default |
|---|---|---|---|
| data | Yes | ||
| style | No | ||
| theme | No | Set the theme for the chart, optional, default is 'default'. | default |
| title | No | ||
| width | No | ||
| height | No | ||
| axisXTitle | No | ||
| axisYTitle | No |
| Name | Required | Description |
|---|---|---|
| artifact | Yes | |
| provenance | Yes | |
| requestMetadata | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, open-world, non-idempotent, non-destructive. The description adds real operational context beyond that: hosted by Darwin on AntV's public renderer, returns a PNG image, 50-row row limit, bounded image sizes, no API key, no payments. That's exactly the extra context the agent needs.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Purpose, example, and constraints are front-loaded, and each clause carries information. The rendering-vendor and payment sentences are slightly peripheral but still relevant to callers checking auth or cost.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
An output schema exists, and the description states the PNG return, so returns are covered. But with 8 parameters, low schema coverage, and a nested data array whose fields are undocumented in both schema and description, an agent cannot tell what `group` does (series splitting) or how `time` is parsed or rendered. Adequate, not complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is only 13%, so the description must carry parameter meaning, and it only partially does: it echoes the 50-row cap and bounded image sizes already enforced by maxItems/width/height constraints. Nothing explains the data row shape (time/value/group), style.palette, texture, theme options, or axis titles, leaving half the surface undocumented.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ("Generate a line chart") plus the intended purpose ("show trends over time"), which implicitly separates it from the bar/column chart siblings. It doesn't name those siblings explicitly, but the chart type itself is the differentiator.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives clear usage context with a concrete example (ratio of sales to profits over 2000-2016), making the trend-over-time framing actionable. It does not state exclusions or say when to prefer generate_bar_chart or generate_column_chart instead.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
generate_bar_chartgenerate_column_chartgenerate_line_chartCreate, inspect, manage, and render charts and data visualizations as SVG/PNG or interactive embeds.
JSON in. Chart or Page out. Same picture forever. Scientific plots included.
Clean messy tabular data and render publication-ready PNG charts from your AI assistant.
Renders interactive Chart.js charts and dashboards inline in AI conversations. Supports bar, line, area, pie, doughnut, scatter, and radar charts with multi-chart dashboard grids.
Add one secure layer between your agents and this server.
