Skip to main content
Glama

analyze_file_differences

Compare two files and generate detailed statistics on their differences to identify changes quickly.

Instructions

Analyze differences between two files with detailed statistics

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
file1YesFirst file path
file2YesSecond file path

Implementation Reference

  • The main handler function that performs the file difference analysis. It reads two files, performs a line-by-line comparison, categorizes differences as added/removed/modified, computes statistics, and returns a formatted text result.
    async analyzeFileDifferences(file1: string, file2: string): Promise<ToolResult> {
      try {
        const fullPath1 = this.workspaceService.resolvePath(file1);
        const fullPath2 = this.workspaceService.resolvePath(file2);
        
        // Read both files
        const content1 = await fs.readFile(fullPath1, 'utf-8');
        const content2 = await fs.readFile(fullPath2, 'utf-8');
        
        const lines1 = content1.split('\n');
        const lines2 = content2.split('\n');
        
        const result: FileComparisonResult = {
          identical: content1 === content2,
          differences: [],
          stats: {
            linesAdded: 0,
            linesRemoved: 0,
            linesModified: 0
          }
        };
        
        // Simple line-by-line comparison
        const maxLines = Math.max(lines1.length, lines2.length);
        
        for (let i = 0; i < maxLines; i++) {
          const line1 = lines1[i];
          const line2 = lines2[i];
          
          if (line1 === undefined) {
            // Line added in file2
            result.differences.push({
              line: i + 1,
              type: 'added',
              content: line2
            });
            result.stats.linesAdded++;
          } else if (line2 === undefined) {
            // Line removed from file1
            result.differences.push({
              line: i + 1,
              type: 'removed',
              content: line1
            });
            result.stats.linesRemoved++;
          } else if (line1 !== line2) {
            // Line modified
            result.differences.push({
              line: i + 1,
              type: 'modified',
              content: line2,
              oldContent: line1
            });
            result.stats.linesModified++;
          }
        }
        
        // Format the output
        let output = `File Comparison Analysis:\n`;
        output += `File 1: ${file1}\n`;
        output += `File 2: ${file2}\n`;
        output += `Identical: ${result.identical}\n\n`;
        
        if (!result.identical) {
          output += `Statistics:\n`;
          output += `- Lines added: ${result.stats.linesAdded}\n`;
          output += `- Lines removed: ${result.stats.linesRemoved}\n`;
          output += `- Lines modified: ${result.stats.linesModified}\n`;
          output += `- Total differences: ${result.differences.length}\n\n`;
          
          if (result.differences.length <= 50) {
            output += `Differences:\n`;
            for (const diff of result.differences) {
              switch (diff.type) {
                case 'added':
                  output += `+ Line ${diff.line}: ${diff.content}\n`;
                  break;
                case 'removed':
                  output += `- Line ${diff.line}: ${diff.content}\n`;
                  break;
                case 'modified':
                  output += `~ Line ${diff.line}:\n`;
                  output += `  - ${diff.oldContent}\n`;
                  output += `  + ${diff.content}\n`;
                  break;
              }
            }
          } else {
            output += `Too many differences to display (${result.differences.length}). Use compareFiles for detailed diff.`;
          }
        }
        
        return {
          content: [{
            type: 'text',
            text: output,
            _meta: {
              identical: result.identical,
              stats: result.stats,
              differenceCount: result.differences.length
            }
          }]
        };
        
      } catch (error) {
        return {
          isError: true,
          content: [{
            type: 'text',
            text: `File analysis failed: ${error instanceof Error ? error.message : String(error)}`
          }]
        };
      }
    }
  • The FileComparisonResult interface defining the return type structure: identical flag, differences array (with line number, type, content, oldContent), and stats (linesAdded, linesRemoved, linesModified).
    export interface FileComparisonResult {
      identical: boolean;
      differences: Array<{
        line: number;
        type: 'added' | 'removed' | 'modified';
        content: string;
        oldContent?: string;
      }>;
      stats: {
        linesAdded: number;
        linesRemoved: number;
        linesModified: number;
      };
    }
  • src/index.ts:456-457 (registration)
    The tool dispatcher case statement that routes the 'analyze_file_differences' tool name to the fileService.analyzeFileDifferences handler method.
    case 'analyze_file_differences':
      return await this.fileService.analyzeFileDifferences(args.file1, args.file2);
  • The tool definition registration with input schema specifying file1 and file2 as required string parameters.
    {
      name: 'analyze_file_differences',
      description: 'Analyze differences between two files with detailed statistics',
      inputSchema: {
        type: 'object',
        properties: {
          file1: { type: 'string', description: 'First file path' },
          file2: { type: 'string', description: 'Second file path' }
        },
        required: ['file1', 'file2']
      }
    },
Behavior2/5

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

With no annotations, the description fails to disclose behavioral traits like side effects, read-only nature, or limitations. It only mentions 'detailed statistics' without specifying what that entails.

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

Conciseness3/5

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

The description is a single concise sentence, but it is too brief and lacks structure to be fully informative. It earns its place but could be expanded.

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 output schema and annotations, the description does not fully inform the agent about return values, statistics nature, or how it differs from similar tools. This is inadequate for a tool with complex 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?

Input schema has 100% description coverage, so the schema already explains parameters. The description adds no extra meaning beyond 'two files', which is already clear from parameter names.

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 verb 'analyze' and resource 'differences between two files with detailed statistics', which defines its purpose. However, it does not distinguish from sibling tools like 'compare_files' or 'git_diff'.

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 is provided on when to use this tool versus alternatives such as 'compare_files' or 'enhanced_git_diff'. The description lacks explicit usage context, prerequisites, or exclusions.

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/agentics-ai/code-mcp'

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