Skip to main content
Glama
andreycretsu

Cursor Talk to Figma MCP

by andreycretsu

set_annotation

Add or modify annotations on Figma design elements to document requirements, provide feedback, or track changes within the Cursor AI workflow.

Instructions

Create or update an annotation

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nodeIdYesThe ID of the node to annotate
annotationIdNoThe ID of the annotation to update (if updating existing annotation)
labelMarkdownYesThe annotation text in markdown format
categoryIdNoThe ID of the annotation category
propertiesNoAdditional properties for the annotation

Implementation Reference

  • Registration of the MCP tool 'set_annotation' including Zod input schema validation and handler function that forwards the annotation creation/update parameters to the Figma plugin via sendCommandToFigma WebSocket communication.
    server.tool(
      "set_annotation",
      "Create or update an annotation",
      {
        nodeId: z.string().describe("The ID of the node to annotate"),
        annotationId: z.string().optional().describe("The ID of the annotation to update (if updating existing annotation)"),
        labelMarkdown: z.string().describe("The annotation text in markdown format"),
        categoryId: z.string().optional().describe("The ID of the annotation category"),
        properties: z.array(z.object({
          type: z.string()
        })).optional().describe("Additional properties for the annotation")
      },
      async ({ nodeId, annotationId, labelMarkdown, categoryId, properties }) => {
        try {
          const result = await sendCommandToFigma("set_annotation", {
            nodeId,
            annotationId,
            labelMarkdown,
            categoryId,
            properties
          });
          return {
            content: [
              {
                type: "text",
                text: JSON.stringify(result)
              }
            ]
          };
        } catch (error) {
          return {
            content: [
              {
                type: "text",
                text: `Error setting annotation: ${error instanceof Error ? error.message : String(error)}`
              }
            ]
          };
        }
      }
    );
  • Input schema for the 'set_annotation' tool using Zod for parameter validation: nodeId (required), annotationId (optional), labelMarkdown (required), categoryId (optional), properties (optional array).
    {
      nodeId: z.string().describe("The ID of the node to annotate"),
      annotationId: z.string().optional().describe("The ID of the annotation to update (if updating existing annotation)"),
      labelMarkdown: z.string().describe("The annotation text in markdown format"),
      categoryId: z.string().optional().describe("The ID of the annotation category"),
      properties: z.array(z.object({
        type: z.string()
      })).optional().describe("Additional properties for the annotation")
    },
  • Handler function for 'set_annotation' tool: extracts parameters, calls sendCommandToFigma to execute the annotation operation in the Figma plugin, returns success result or error message in MCP content format.
    async ({ nodeId, annotationId, labelMarkdown, categoryId, properties }) => {
      try {
        const result = await sendCommandToFigma("set_annotation", {
          nodeId,
          annotationId,
          labelMarkdown,
          categoryId,
          properties
        });
        return {
          content: [
            {
              type: "text",
              text: JSON.stringify(result)
            }
          ]
        };
      } catch (error) {
        return {
          content: [
            {
              type: "text",
              text: `Error setting annotation: ${error instanceof Error ? error.message : String(error)}`
            }
          ]
        };
      }
    }

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv1.0.0
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / annotationId
      Added value: +{
      +  "description": "The ID of the annotation to update (if updating existing annotation)",
      +  "type": "string"
      +}
    • addedInput schema / properties / categoryId
      Added value: +{
      +  "description": "The ID of the annotation category",
      +  "type": "string"
      +}
    • addedInput schema / properties / labelMarkdown
      Added value: +{
      +  "description": "The annotation text in markdown format",
      +  "type": "string"
      +}
    • addedInput schema / properties / nodeId
      Added value: +{
      +  "description": "The ID of the node to annotate",
      +  "type": "string"
      +}
    • addedInput schema / properties / properties
      Added value: +{
      +  "description": "Additional properties for the annotation",
      +  "items": {
      +    "properties": {
      +      "type": {
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "type"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / required
      Added value: +[
      +  "nodeId",
      +  "labelMarkdown"
      +]
  2. First observed

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are provided, so the description carries full behavioral disclosure burden. It merely says 'create or update' without revealing key traits such as upsert behavior, whether annotationId is required for updates, or what happens if no annotationId is supplied, creating ambiguity.

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, succinct sentence that front-loads the core action. It is efficient, though for a tool with five parameters it could benefit from a bit more context while remaining concise.

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?

With five parameters, create/update semantics, no output schema, and no annotations, this description is far from complete. It does not explain the distinction between create and update flows, required parameters for each path, or any side effects.

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 100%, so the baseline is 3. The description adds no extra meaning about parameter relationships (e.g., that annotationId is needed for updates or categoryId for creation), but the schema already documents each parameter individually.

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

Purpose4/5

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

The description clearly states the action ('create or update') and resource ('annotation'), making the core purpose understandable. However, it does not explicitly differentiate this from the sibling tool 'set_multiple_annotations', which also deals with annotations.

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 like 'set_multiple_annotations' or 'get_annotations'. It also fails to mention prerequisites or context, leaving the agent to infer when this tool is appropriate.

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