Skip to main content
Glama

image_recognition

Analyzes and describes images using Google Gemini AI by processing file paths and custom prompts, enabling detailed content recognition for diverse use cases.

Instructions

Analyze and describe images using Google Gemini AI

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
filepathYesPath to the media file to analyze
modelnameNoGemini model to use for recognitiongemini-2.0-flash
promptNoCustom prompt for the recognitionDescribe this content

Implementation Reference

  • The main handler function (callback) that implements the image_recognition tool logic. It validates the image file, uploads it using GeminiService, processes it with a prompt, and returns the result or error.
    callback: async (args: ImageRecognitionParams): Promise<CallToolResult> => {
      try {
        log.info(`Processing image recognition request for file: ${args.filepath}`);
        log.verbose('Image recognition request', JSON.stringify(args));
        
        // Verify file exists
        if (!fs.existsSync(args.filepath)) {
          throw new Error(`Image file not found: ${args.filepath}`);
        }
        
        // Verify file is an image
        const ext = path.extname(args.filepath).toLowerCase();
        if (!['.jpg', '.jpeg', '.png', '.webp'].includes(ext)) {
          throw new Error(`Unsupported image format: ${ext}. Supported formats are: .jpg, .jpeg, .png, .webp`);
        }
        
        // Default prompt if not provided
        const prompt = args.prompt || 'Describe this image';
        const modelName = args.modelname || 'gemini-2.0-flash';
        
        // Upload the file
        log.info('Uploading image file...');
        const file = await geminiService.uploadFile(args.filepath);
        
        // Process with Gemini
        log.info('Generating content from image...');
        const result = await geminiService.processFile(file, prompt, modelName);
        
        if (result.isError) {
          log.error(`Error in image recognition: ${result.text}`);
          return {
            content: [
              {
                type: 'text',
                text: result.text
              }
            ],
            isError: true
          };
        }
        
        log.info('Image recognition completed successfully');
        log.verbose('Image recognition result', JSON.stringify(result));
        
        return {
          content: [
            {
              type: 'text',
              text: result.text
            }
          ]
        };
      } catch (error) {
        log.error('Error in image recognition tool', error);
        const errorMessage = error instanceof Error ? error.message : String(error);
        
        return {
          content: [
            {
              type: 'text',
              text: `Error processing image: ${errorMessage}`
            }
          ],
          isError: true
        };
      }
    }
  • Zod schema for input parameters of the image_recognition tool. Extends the common RecognitionParamsSchema with filepath, optional prompt, and modelname.
    export const ImageRecognitionParamsSchema = RecognitionParamsSchema.extend({});
    export type ImageRecognitionParams = z.infer<typeof ImageRecognitionParamsSchema>;
  • src/server.ts:58-62 (registration)
    Registration of the image_recognition tool with the MCP server using mcpServer.tool() method, passing name, description, inputSchema, and callback.
    this.mcpServer.tool(
      imageRecognitionTool.name,
      imageRecognitionTool.description,
      imageRecognitionTool.inputSchema.shape,
      imageRecognitionTool.callback
  • src/server.ts:53-53 (registration)
    Creation of the imageRecognitionTool instance using createImageRecognitionTool factory function before registration.
    const imageRecognitionTool = createImageRecognitionTool(this.geminiService);
  • Factory function that creates the full tool definition object for image_recognition, including name, description, schema, and handler callback.
    export const createImageRecognitionTool = (geminiService: GeminiService) => {
      return {
        name: 'image_recognition',
        description: 'Analyze and describe images using Google Gemini AI',
        inputSchema: ImageRecognitionParamsSchema,
        callback: async (args: ImageRecognitionParams): Promise<CallToolResult> => {
          try {
            log.info(`Processing image recognition request for file: ${args.filepath}`);
            log.verbose('Image recognition request', JSON.stringify(args));
            
            // Verify file exists
            if (!fs.existsSync(args.filepath)) {
              throw new Error(`Image file not found: ${args.filepath}`);
            }
            
            // Verify file is an image
            const ext = path.extname(args.filepath).toLowerCase();
            if (!['.jpg', '.jpeg', '.png', '.webp'].includes(ext)) {
              throw new Error(`Unsupported image format: ${ext}. Supported formats are: .jpg, .jpeg, .png, .webp`);
            }
            
            // Default prompt if not provided
            const prompt = args.prompt || 'Describe this image';
            const modelName = args.modelname || 'gemini-2.0-flash';
            
            // Upload the file
            log.info('Uploading image file...');
            const file = await geminiService.uploadFile(args.filepath);
            
            // Process with Gemini
            log.info('Generating content from image...');
            const result = await geminiService.processFile(file, prompt, modelName);
            
            if (result.isError) {
              log.error(`Error in image recognition: ${result.text}`);
              return {
                content: [
                  {
                    type: 'text',
                    text: result.text
                  }
                ],
                isError: true
              };
            }
            
            log.info('Image recognition completed successfully');
            log.verbose('Image recognition result', JSON.stringify(result));
            
            return {
              content: [
                {
                  type: 'text',
                  text: result.text
                }
              ]
            };
          } catch (error) {
            log.error('Error in image recognition tool', error);
            const errorMessage = error instanceof Error ? error.message : String(error);
            
            return {
              content: [
                {
                  type: 'text',
                  text: `Error processing image: ${errorMessage}`
                }
              ],
              isError: true
            };
          }
        }
      };
    };

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.2/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden. It only mentions 'using Google Gemini AI' but does not disclose safety (e.g., read-only vs destructive), API costs, file size limits, or the nature of the analysis (e.g., real-time, batch).

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?

Single sentence, front-loaded with verb and resource. No wasted words. Efficient and scannable.

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?

No output schema is provided, yet the description does not explain what the tool returns (e.g., text description, confidence scores). For a tool with 3 parameters and no annotations, this leaves the agent guessing about the response format and behavior.

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% with each parameter described. The description adds no additional meaning beyond the schema; it only names the AI provider. Baseline of 3 is appropriate.

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

Purpose5/5

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

The description clearly states the action ('Analyze and describe images') and the technology ('using Google Gemini AI'). It distinguishes from sibling tools (audio_recognition, video_recognition) by specifying the media type (images).

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?

No guidance on when to use this tool versus alternatives (e.g., audio_recognition, video_recognition). No mention of prerequisites, limitations, or scenarios where it is not appropriate.

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

Deploy Server

Other Tools

Related Tools