Skip to main content
Glama

add_paragraph

Insert formatted text paragraphs into Word documents by specifying file path, content, and styling options like alignment.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
filePathYes
textYes
styleNo
alignmentNo

Implementation Reference

  • The core handler function for the 'add_paragraph' tool. It reads the existing document file, creates a new DOCX document containing a single paragraph with the specified text, style, and alignment, then overwrites the original file with this new content.
    async addParagraph(filePath: string, options: ParagraphOptions): Promise<APIResponse> {
      try {
        const buffer = await fs.readFile(filePath);
        const doc = new Document({
          sections: [{
            properties: {},
            children: [
              new Paragraph({
                text: options.text,
                style: options.style,
                alignment: options.alignment,
              }),
            ],
          }],
        });
    
        await Packer.toBuffer(doc).then((buffer) => {
          return fs.writeFile(filePath, buffer);
        });
    
        return { success: true };
      } catch (error) {
        const err = error as Error;
        return { success: false, error: `添加段落失败: ${err.message}` };
      }
    }
  • TypeScript interface defining the structure and types for ParagraphOptions used as input to the addParagraph handler.
    export interface ParagraphOptions {
      text: string;
      style?: string;
      alignment?: 'left' | 'center' | 'right' | 'start' | 'end' | 'both' | 'mediumKashida' | 'distribute' | 'numTab' | 'highKashida' | 'lowKashida' | 'thaiDistribute';
      fontSize?: number;
      bold?: boolean;
      italic?: boolean;
    }
  • MCP server registration of the 'add_paragraph' tool, including Zod input schema validation and a wrapper function that invokes the DocumentService handler and formats the MCP response.
      "add_paragraph",
      {
        filePath: z.string(),
        text: z.string(),
        style: z.string().optional(),
        alignment: z.enum(['left', 'center', 'right', 'start', 'end', 'both', 'mediumKashida', 'distribute', 'numTab', 'highKashida', 'lowKashida', 'thaiDistribute']).optional(),
      },
      async (params) => {
        const result = await docService.addParagraph(params.filePath, {
          text: params.text,
          style: params.style,
          alignment: params.alignment,
        });
        return {
          content: [
            {
              type: "text",
              text: result.success ? "段落已添加" : result.error!,
            },
          ],
          isError: !result.success,
        };
      }
    );
  • src/server.ts:39-50 (registration)
    Tool schema definition and registration in the HTTP server's tools list for 'add_paragraph', used for /tools/list endpoint and dispatched in the switch statement.
    name: 'add_paragraph',
    description: '向文档添加段落',
    parameters: {
      properties: {
        filePath: { type: 'string', description: '文档路径' },
        text: { type: 'string', description: '段落文本' },
        style: { type: 'string', description: '段落样式' },
        alignment: { type: 'string', description: '对齐方式' },
      },
      required: ['filePath', 'text'],
      type: 'object',
    },
  • src/server.ts:133-139 (registration)
    Dispatch handler in the HTTP server's /tools/call endpoint that routes 'add_paragraph' calls to the DocumentService.addParagraph method.
    case 'add_paragraph':
      result = await docService.addParagraph(parameters.filePath, {
        text: parameters.text,
        style: parameters.style,
        alignment: parameters.alignment,
      });
      break;
Behavior1/5

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

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

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

Completeness1/5

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

Tool has no description.

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

Parameters1/5

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

Tool has no description.

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

Purpose1/5

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

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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/puchunjie/doc-tools-mcp'

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