Skip to main content
Glama
webflow

Webflow

Official
by webflow

Designer Style Tool

style_tool

Create, retrieve, and update CSS styles for Webflow sites to manage design consistency across breakpoints and pseudo-classes.

Instructions

Designer Tool - Style tool to perform actions like create style, get all styles, update styles

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
siteIdYesThe ID of the site. DO NOT ASSUME site id. ALWAYS ask user for site id if not already provided or known. use sites_list tool to fetch all sites and then ask user to select one of them.
actionsYes

Implementation Reference

  • The handler function for the style_tool that processes input, calls the internal RPC proxy (styleToolRPCCall), formats the response, and handles errors.
    async ({ siteId, actions }) => {
      try {
        return formatResponse(await styleToolRPCCall(siteId, actions));
      } catch (error) {
        return formatErrorResponse(error);
      }
    }
  • Detailed Zod input schema for the style_tool, defining siteId and actions array supporting create_style, get_styles, and update_style operations with properties, breakpoints, pseudos, etc.
    inputSchema: z.object({
      ...SiteIdSchema,
      actions: z.array(
        z.object({
          create_style: z
            .object({
              name: z.string().describe("The name of the style"),
              properties: z
                .array(
                  z.object({
                    property_name: z
                      .string()
                      .describe("The name of the property"),
                    property_value: z
                      .string()
                      .optional()
                      .describe("The value of the property"),
                    variable_as_value: z
                      .string()
                      .optional()
                      .describe("The variable id to use as the value"),
                  })
                )
                .describe(
                  "The properties of the style. if you are looking to link a variable as the value, then use the variable_as_value field. but do not use both property_value and variable_as_value"
                ),
              parent_style_name: z
                .string()
                .optional()
                .describe(
                  "The name of the parent style to create the new style in. this will use to create combo class"
                ),
            })
            .optional()
            .describe("Create a new style"),
          get_styles: z
            .object({
              skip_properties: z
                .boolean()
                .optional()
                .describe(
                  "Whether to skip the properties of the style. to get minimal data."
                ),
              include_all_breakpoints: z
                .boolean()
                .optional()
                .describe(
                  "Whether to include all breakpoints styles or not. very data intensive."
                ),
              query: z
                .enum(["all", "filtered"])
                .describe("The query to get all styles or filtered styles"),
              filter_ids: z
                .array(z.string())
                .optional()
                .describe(
                  "The ids of the styles to filter by. should be used with query filtered"
                ),
            })
            .optional()
            .describe("Get all styles"),
          update_style: z
            .object({
              style_name: z
                .string()
                .describe("The name of the style to update"),
              breakpoint_id: z
                .enum([
                  "xxl",
                  "xl",
                  "large",
                  "main",
                  "medium",
                  "small",
                  "tiny",
                ])
                .optional()
                .describe("The breakpoint to update the style for"),
              pseudo: z
                .enum([
                  "noPseudo",
                  "nth-child(odd)",
                  "nth-child(even)",
                  "first-child",
                  "last-child",
                  "hover",
                  "active",
                  "pressed",
                  "visited",
                  "focus",
                  "focus-visible",
                  "focus-within",
                  "placeholder",
                  "empty",
                  "before",
                  "after",
                ])
                .optional()
                .describe("The pseudo class to update the style for"),
              properties: z
                .array(
                  z.object({
                    property_name: z
                      .string()
                      .describe("The name of the property"),
                    property_value: z
                      .string()
                      .optional()
                      .describe("The value of the property"),
                    variable_as_value: z
                      .string()
                      .optional()
                      .describe("The variable id to use as the value"),
                  })
                )
                .optional()
                .describe("The properties to update or add to the style for"),
              remove_properties: z
                .array(z.string())
                .optional()
                .describe("The properties to remove from the style"),
            })
            .optional()
            .describe("Update a style"),
        })
      ),
    }),
  • Core registration of the style_tool with MCP server, specifying name, title, description, inputSchema, and handler.
    server.registerTool(
      "style_tool",
      {
        title: "Designer Style Tool",
        description:
          "Designer Tool - Style tool to perform actions like create style, get all styles, update styles",
        inputSchema: z.object({
          ...SiteIdSchema,
          actions: z.array(
            z.object({
              create_style: z
                .object({
                  name: z.string().describe("The name of the style"),
                  properties: z
                    .array(
                      z.object({
                        property_name: z
                          .string()
                          .describe("The name of the property"),
                        property_value: z
                          .string()
                          .optional()
                          .describe("The value of the property"),
                        variable_as_value: z
                          .string()
                          .optional()
                          .describe("The variable id to use as the value"),
                      })
                    )
                    .describe(
                      "The properties of the style. if you are looking to link a variable as the value, then use the variable_as_value field. but do not use both property_value and variable_as_value"
                    ),
                  parent_style_name: z
                    .string()
                    .optional()
                    .describe(
                      "The name of the parent style to create the new style in. this will use to create combo class"
                    ),
                })
                .optional()
                .describe("Create a new style"),
              get_styles: z
                .object({
                  skip_properties: z
                    .boolean()
                    .optional()
                    .describe(
                      "Whether to skip the properties of the style. to get minimal data."
                    ),
                  include_all_breakpoints: z
                    .boolean()
                    .optional()
                    .describe(
                      "Whether to include all breakpoints styles or not. very data intensive."
                    ),
                  query: z
                    .enum(["all", "filtered"])
                    .describe("The query to get all styles or filtered styles"),
                  filter_ids: z
                    .array(z.string())
                    .optional()
                    .describe(
                      "The ids of the styles to filter by. should be used with query filtered"
                    ),
                })
                .optional()
                .describe("Get all styles"),
              update_style: z
                .object({
                  style_name: z
                    .string()
                    .describe("The name of the style to update"),
                  breakpoint_id: z
                    .enum([
                      "xxl",
                      "xl",
                      "large",
                      "main",
                      "medium",
                      "small",
                      "tiny",
                    ])
                    .optional()
                    .describe("The breakpoint to update the style for"),
                  pseudo: z
                    .enum([
                      "noPseudo",
                      "nth-child(odd)",
                      "nth-child(even)",
                      "first-child",
                      "last-child",
                      "hover",
                      "active",
                      "pressed",
                      "visited",
                      "focus",
                      "focus-visible",
                      "focus-within",
                      "placeholder",
                      "empty",
                      "before",
                      "after",
                    ])
                    .optional()
                    .describe("The pseudo class to update the style for"),
                  properties: z
                    .array(
                      z.object({
                        property_name: z
                          .string()
                          .describe("The name of the property"),
                        property_value: z
                          .string()
                          .optional()
                          .describe("The value of the property"),
                        variable_as_value: z
                          .string()
                          .optional()
                          .describe("The variable id to use as the value"),
                      })
                    )
                    .optional()
                    .describe("The properties to update or add to the style for"),
                  remove_properties: z
                    .array(z.string())
                    .optional()
                    .describe("The properties to remove from the style"),
                })
                .optional()
                .describe("Update a style"),
            })
          ),
        }),
      },
      async ({ siteId, actions }) => {
        try {
          return formatResponse(await styleToolRPCCall(siteId, actions));
        } catch (error) {
          return formatErrorResponse(error);
        }
      }
    );
  • Helper function that proxies the style_tool call to the RPC backend.
    const styleToolRPCCall = async (siteId: string, actions: any) => {
      return rpc.callTool("style_tool", {
        siteId,
        actions: actions || [],
      });
    };
  • src/mcp.ts:64-64 (registration)
    Top-level call to registerDEStyleTools within registerDesignerTools, which includes the style_tool.
    registerDEStyleTools(server, rpc);
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description mentions actions like create, get all, and update, implying both read and write operations, but doesn't specify permissions required, whether changes are reversible, rate limits, or what happens on errors. For a tool with multiple mutation capabilities, this lack of behavioral context is a significant gap.

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?

The description is a single, efficient sentence that lists the key actions. It's appropriately sized and front-loaded with the main purpose. However, it could be more structured by explicitly separating the actions or adding brief context, but it avoids unnecessary verbosity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of the input schema with nested objects for multiple actions, no annotations, and no output schema, the description is incomplete. It doesn't explain the tool's scope, return values, or how the actions interact. For a multi-action tool with significant parameter complexity, this description is inadequate and leaves too much for the agent to infer.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 50%, so the description must compensate but doesn't add meaningful parameter semantics beyond what's implied by the tool name. The description lists actions (create, get all, update) which loosely map to the 'actions' parameter, but it doesn't explain the 'siteId' parameter or provide usage examples. The description adds minimal value over the schema, which already documents parameters well.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the tool performs actions like create, get all, and update styles, which gives a general purpose but lacks specificity about what 'styles' are in this context. It doesn't distinguish this tool from sibling tools like 'de_learn_more_about_styles' or 'element_tool', which might also handle styles. The description is vague about the exact resource being manipulated.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites like needing a site ID or how this tool relates to sibling tools such as 'de_learn_more_about_styles' or 'variable_tool'. There's no explicit when-to-use or when-not-to-use information, leaving the agent to guess based on the tool name alone.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/webflow/mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server