Skip to main content
Glama

drive_files_create

Creates a Google Drive file with specified name, MIME type, and parent folder. Optionally uploads a local file. Returns requested fields like ID or webViewLink.

Instructions

Create a new file in Google Drive. Use with bodyParams for metadata and optionally upload a local file.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fieldsNoFields to return (e.g. "id,webViewLink")
nameYesFile name
mimeTypeNoMIME type (e.g. "application/vnd.google-apps.document")
parentsNoParent folder IDs (JSON array as string, e.g. '["folderId"]')
uploadPathNoLocal file path to upload

Implementation Reference

  • Tool definition (schema) for drive_files_create. Defines the tool name, description, command (drive files create), params (fields), bodyParams (name, mimeType, parents), supportsUpload flag, and defaultParams (supportsAllDrives).
    {
      name: "drive_files_create",
      description: "Create a new file in Google Drive. Use with bodyParams for metadata and optionally upload a local file.",
      command: ["drive", "files", "create"],
      params: [
        { name: "fields", description: "Fields to return (e.g. \"id,webViewLink\")", type: "string", required: false },
      ],
      bodyParams: [
        { name: "name", description: "File name", type: "string", required: true },
        { name: "mimeType", description: "MIME type (e.g. \"application/vnd.google-apps.document\")", type: "string", required: false },
        { name: "parents", description: "Parent folder IDs (JSON array as string, e.g. '[\"folderId\"]')", type: "string", required: false },
      ],
      supportsUpload: true,
      defaultParams: DRIVE_SHARED_DEFAULTS_NO_INCLUDE,
    },
  • src/index.ts:156-178 (registration)
    Generic registration loop that registers all tools (including drive_files_create) from tools array onto the MCP server using server.tool(), with buildZodSchema for schema and executeGws for handler logic.
    // Register each tool
    for (const tool of tools) {
      const schema = buildZodSchema(tool);
    
      server.tool(
        tool.name,
        tool.description,
        schema,
        async (args) => {
          const result = await executeGws(tool, args as Record<string, unknown>, gwsBinary);
    
          if (result.success) {
            return {
              content: [{ type: "text" as const, text: result.output || "(empty response)" }],
            };
          } else {
            return {
              content: [{ type: "text" as const, text: `Error: ${result.error}` }],
              isError: true,
            };
          }
        },
      );
  • buildZodSchema helper that constructs the Zod validation schema for each tool. For drive_files_create, this includes 'fields' (from params), 'name', 'mimeType', 'parents' (from bodyParams), plus optional 'uploadPath' since supportsUpload is true.
    export function buildZodSchema(tool: ToolDef): Record<string, z.ZodTypeAny> {
      const shape: Record<string, z.ZodTypeAny> = {};
    
      const allParams = [...tool.params, ...(tool.bodyParams || [])];
    
      for (const p of allParams) {
        let field: z.ZodTypeAny;
        switch (p.type) {
          case "number":
            field = z.number().describe(p.description);
            break;
          case "boolean":
            field = z.boolean().describe(p.description);
            break;
          default:
            field = z.string().describe(p.description);
        }
    
        if (!p.required) {
          field = field.optional();
        }
    
        shape[p.name] = field;
      }
    
      // Add optional uploadPath for tools that support file upload
      if (tool.supportsUpload) {
        shape.uploadPath = z.string().describe("Local file path to upload").optional();
      }
    
      return shape;
    }
  • executeGws handles the actual execution for drive_files_create (and all generic tools). It calls buildArgs to construct CLI arguments, spawns the gws process, and returns the output. This is the generic handler invoked by the registered tool callback.
    export async function executeGws(
      tool: ToolDef,
      args: Record<string, unknown>,
      gwsBinary: string,
    ): Promise<ExecResult> {
      const cliArgs = buildArgs(tool, args);
    
      console.error(`[gws-mcp] Executing: ${gwsBinary} ${cliArgs.join(" ")}`);
    
      try {
        const { stdout, stderr } = await spawnGwsRaw(gwsBinary, cliArgs);
    
        if (stderr) {
          console.error(`[gws-mcp] stderr: ${stderr}`);
        }
    
        return { success: true, output: stdout || "(empty response)" };
      } catch (err: unknown) {
        const error = err as { message?: string };
        let message = error.message || "Unknown error";
    
        // Enhance Drive 404 errors with actionable hints
        if (message.includes("404") && message.includes("not found") && tool.command[0] === "drive") {
          message += "\n\nHint: If this file is in a shared drive, ensure supportsAllDrives is set (this should be automatic). Check that the file ID is correct and the authenticated account has access.";
        }
    
        console.error(`[gws-mcp] Error: ${message}`);
        return { success: false, output: "", error: message };
      }
    }
Behavior2/5

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

With no annotations, the description should disclose behavioral traits. It mentions optional file upload but does not specify required permissions, idempotency, or side effects beyond creation. The term 'bodyParams' is ambiguous and not present in the schema.

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 concise with two sentences, no redundancies. However, 'Use with bodyParams' is unnecessary jargon that could confuse agents.

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 5 parameters and no output schema, the description should provide more context on usage, return values, and prerequisites. It only covers the basic creation action and optional upload, missing key details like required permissions or folder placement.

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 coverage is 100%, so baseline is 3. The description adds minimal value by mentioning optional file upload corresponding to 'uploadPath'. However, 'bodyParams' is misleading as it is not a parameter, reducing clarity.

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 creates a new file in Google Drive, specifying the resource and action. It distinguishes from siblings like 'drive_files_copy' and 'drive_files_update' by focusing on creation, but does not explicitly differentiate from them.

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 (e.g., 'drive_files_copy' for copying, 'sheets_values_append' for appending to sheets). It lacks exclusion criteria or usage context.

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/conorbronsdon/gws-mcp-server'

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