Skip to main content
Glama

pdf-to-markdown

Convert PDF files to Markdown format for easier editing and sharing. Extract text content from PDFs and transform it into readable Markdown text.

Instructions

Convert a PDF file to markdown

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
filepathYesAbsolute path of the PDF file to convert

Implementation Reference

  • Handler dispatch for pdf-to-markdown tool (shared with other file-to-markdown tools): validates input filepath and delegates to Markdownify.toMarkdown using filePath parameter.
    case tools.PDFToMarkdownTool.name:
    case tools.ImageToMarkdownTool.name:
    case tools.AudioToMarkdownTool.name:
    case tools.DocxToMarkdownTool.name:
    case tools.XlsxToMarkdownTool.name:
    case tools.PptxToMarkdownTool.name:
      if (!validatedArgs.filepath) {
        throw new Error("File path is required for this tool");
      }
      result = await Markdownify.toMarkdown({
        filePath: validatedArgs.filepath,
        projectRoot: validatedArgs.projectRoot,
        uvPath: validatedArgs.uvPath || process.env.UV_PATH,
      });
      break;
  • Schema definition for the pdf-to-markdown tool, specifying input as absolute filepath of the PDF.
    export const PDFToMarkdownTool = ToolSchema.parse({
      name: "pdf-to-markdown",
      description: "Convert a PDF file to markdown",
      inputSchema: {
        type: "object",
        properties: {
          filepath: {
            type: "string",
            description: "Absolute path of the PDF file to convert",
          },
        },
        required: ["filepath"],
      },
    });
  • src/server.ts:33-37 (registration)
    Tool registration via listTools handler: exposes all tools from tools.ts, including pdf-to-markdown.
    server.setRequestHandler(ListToolsRequestSchema, async () => {
      return {
        tools: Object.values(tools),
      };
    });
  • Core conversion logic in Markdownify.toMarkdown: for filePath (used by pdf-to-markdown), sets inputPath to filePath, calls _markitdown to run markitdown converter, saves output to temp MD file.
    static async toMarkdown({
      filePath,
      url,
      projectRoot = path.resolve(__dirname, ".."),
      uvPath = "~/.local/bin/uv",
    }: {
      filePath?: string;
      url?: string;
      projectRoot?: string;
      uvPath?: string;
    }): Promise<MarkdownResult> {
      try {
        let inputPath: string;
        let isTemporary = false;
    
        if (url) {
          const response = await fetch(url);
    
          let extension = null;
    
          if (url.endsWith(".pdf")) {
            extension = "pdf";
          }
    
          const arrayBuffer = await response.arrayBuffer();
          const content = Buffer.from(arrayBuffer);
    
          inputPath = await this.saveToTempFile(content, extension);
          isTemporary = true;
        } else if (filePath) {
          inputPath = filePath;
        } else {
          throw new Error("Either filePath or url must be provided");
        }
    
        const text = await this._markitdown(inputPath, projectRoot, uvPath);
        const outputPath = await this.saveToTempFile(text);
    
        if (isTemporary) {
          fs.unlinkSync(inputPath);
        }
    
        return { path: outputPath, text };
      } catch (e: unknown) {
        if (e instanceof Error) {
          throw new Error(`Error processing to Markdown: ${e.message}`);
        } else {
          throw new Error("Error processing to Markdown: Unknown error occurred");
        }
      }
    }
  • Executes the markitdown binary via 'uv run' to perform the actual PDF to markdown conversion.
    private static async _markitdown(
      filePath: string,
      projectRoot: string,
      uvPath: string,
    ): Promise<string> {
      const venvPath = path.join(projectRoot, ".venv");
      const markitdownPath = path.join(
        venvPath,
        process.platform === "win32" ? "Scripts" : "bin",
        `markitdown${process.platform === "win32" ? ".exe" : ""}`,
      );
    
      if (!fs.existsSync(markitdownPath)) {
        throw new Error("markitdown executable not found");
      }
    
      // Expand tilde in uvPath if present
      const expandedUvPath = expandHome(uvPath);
    
      // Use execFile to prevent command injection
      const { stdout, stderr } = await execFileAsync(expandedUvPath, [
        "run",
        markitdownPath,
        filePath,
      ]);
    
      if (stderr) {
        throw new Error(`Error executing command: ${stderr}`);
      }
    
      return stdout;
    }
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. It states the conversion action but lacks critical details: whether this is a read-only operation, if it modifies the original PDF, what permissions are needed, how errors are handled, or what the output format entails (e.g., markdown structure, quality of conversion). For a tool with no annotation coverage, this 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.

Conciseness5/5

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

The description is a single, efficient sentence with zero waste. It is appropriately sized and front-loaded, directly stating the tool's purpose without unnecessary elaboration. Every word earns its place, making it easy to parse quickly.

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 lack of annotations and output schema, the description is incomplete for a file conversion tool. It doesn't explain what the markdown output looks like (e.g., formatting, metadata), potential limitations (e.g., complex PDFs, images within PDFs), or error conditions. With no structured data to compensate, the description should provide more context about the tool's behavior and results.

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?

The schema description coverage is 100%, with the single parameter 'filepath' fully documented in the schema as 'Absolute path of the PDF file to convert'. The description adds no additional parameter semantics beyond what the schema provides, such as file size limits, supported PDF versions, or path format examples. Baseline 3 is appropriate when the schema does the heavy lifting.

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 tool's purpose with a specific verb ('Convert') and resource ('a PDF file to markdown'), making it immediately understandable. It distinguishes from most siblings by specifying PDF input, though it doesn't explicitly differentiate from other file conversion tools like docx-to-markdown or pptx-to-markdown beyond the file type.

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. With multiple sibling tools for converting different file types to markdown (e.g., docx-to-markdown, pptx-to-markdown), there's no indication of when PDF conversion is appropriate or what distinguishes it from other conversion tools. No prerequisites or exclusions are mentioned.

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/zcaceres/markdownify-mcp'

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