plot_box_plotCreate a box plot for comparing distributions (requires matplotlib).
| Name | Required | Description | Default |
|---|---|---|---|
| color | No | Box color (name or hex code, e.g., 'blue', '#2E86AB') | |
| title | No | Chart title string, e.g., 'Distribution Comparison' | Box Plot |
| y_label | No | Y-axis label, e.g., 'Values' | Values |
| data_groups | Yes | List of data groups to compare, e.g., [[1, 2, 3], [4, 5, 6]] | |
| group_labels | No | Labels for each group, e.g., ['Group A', 'Group B'] |
Changes observed during successful MCP inspections.
Input schema / properties / color / descriptionAdded value: +"Box color (name or hex code, e.g., 'blue', '#2E86AB')"Input schema / properties / data_groups / descriptionAdded value: +"List of data groups to compare, e.g., [[1, 2, 3], [4, 5, 6]]"Input schema / properties / group_labels / descriptionAdded value: +"Labels for each group, e.g., ['Group A', 'Group B']"Input schema / properties / title / descriptionAdded value: +"Chart title string, e.g., 'Distribution Comparison'"Input schema / properties / y_label / descriptionAdded value: +"Y-axis label, e.g., 'Values'"Output schema / (root)Previous value: -{
- "additionalProperties": true,
- "type": "object"
-}New value: +nullInput schema / additionalPropertiesAdded value: +falseInput schema / properties / color / titleRemoved value: -"Color"Input schema / properties / data_groups / titleRemoved value: -"Data Groups"Input schema / properties / group_labels / titleRemoved value: -"Group Labels"Input schema / properties / title / titleRemoved value: -"Title"Input schema / properties / y_label / titleRemoved value: -"Y Label"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and idempotentHint, so the safety profile is covered. The description adds one piece of genuine context, the matplotlib dependency ('requires matplotlib'), but says nothing about what is produced or returned (figure, image, file path).
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?
A single front-loaded sentence with no wasted words; the intent and the dependency are both packed in. It is efficient though not rich enough to warrant a 5.
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?
For a plotting tool with no output schema and read-only annotations, the description omits the return format (rendered image vs figure object), which is the key unknown an agent faces. Parameters and safety are adequately covered by schema and annotations, so the gap is limited but real.
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 100%, so all five parameters are already documented in the schema with examples. The description adds no additional parameter meaning, so the baseline of 3 applies.
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 ('Create') and resource ('box plot') plus its analytical intent ('comparing distributions'), which differentiates it from plot_histogram and plot_scatter siblings by chart type. It stops short of explicitly naming which sibling to use instead for other distribution views.
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?
'for comparing distributions' implies when a box plot is appropriate, giving some selection signal against histogram/line siblings. However, there is no explicit when-to-use/when-not guidance or mention of alternatives, leaving routing to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.