Skip to main content
Glama

trace_file

Analyze TypeScript files to detect schema mismatches between data producers and consumers, preventing runtime errors by validating contracts during development.

Instructions

Trace MCP tool usage in a single TypeScript file.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
filePathYesPath to a TypeScript file

Implementation Reference

  • Main handler switch case for the 'trace_file' tool. Validates input using TraceFileInput schema, invokes traceFromFile helper, formats consumer usage data as JSON, and returns it.
    case 'trace_file': {
      const input = TraceFileInput.parse(args);
      log(`Tracing file: ${input.filePath}`);
      
      const usage = await traceFromFile(input.filePath);
      
      return {
        content: [
          {
            type: 'text',
            text: JSON.stringify({
              success: true,
              count: usage.length,
              usage,
            }, null, 2),
          },
        ],
      };
    }
  • Zod input validation schema for the trace_file tool requiring a filePath.
    const TraceFileInput = z.object({
      filePath: z.string().describe('Path to a single TypeScript file to trace tool usage in'),
    });
  • src/index.ts:167-177 (registration)
    Registration of the trace_file tool in the ListTools response, defining name, description, and JSON inputSchema.
    {
      name: 'trace_file',
      description: 'Trace MCP tool usage in a single TypeScript file.',
      inputSchema: {
        type: 'object',
        properties: {
          filePath: { type: 'string', description: 'Path to a TypeScript file' },
        },
        required: ['filePath'],
      },
    },
  • Helper function invoked by the handler. Defaults to TypeScript parser, traces usage by scanning parent directory but including only the target file, filters results to that file.
    export async function traceFromFile(filePath: string, language?: string): Promise<ConsumerSchema[]> {
      // For backward compatibility, default to TypeScript
      const lang = language || 'typescript';
    
      if (!hasParser(lang)) {
        throw new Error(
          `No parser available for language: ${lang}. Make sure to call bootstrapLanguageParsers() at startup.`
        );
      }
    
      const parser = getParser(lang);
    
      // Extract from the directory containing the file
      const rootDir = filePath.substring(0, filePath.lastIndexOf('/') || filePath.lastIndexOf('\\'));
      const fileName = filePath.substring((filePath.lastIndexOf('/') || filePath.lastIndexOf('\\')) + 1);
    
      const allSchemas = await parser.traceUsage({
        rootDir: rootDir || '.',
        include: [fileName],
      });
    
      return allSchemas.filter(s => s.callSite.file === filePath);
    }
  • Core TypeScript-specific tracing logic. Scans AST for callTool expressions, parses tool name and arguments, traces expected output properties via result usage analysis.
    private traceFile(sourceFile: SourceFile, filePath: string): ConsumerSchema[] {
      const schemas: ConsumerSchema[] = [];
    
      // Find all callTool() calls
      sourceFile.forEachDescendant((node) => {
        if (Node.isCallExpression(node)) {
          const callInfo = this.parseCallToolExpression(node);
          if (callInfo) {
            // Track how the result is used
            const expectedProps = this.traceResultUsage(node);
    
            schemas.push({
              toolName: callInfo.toolName,
              callSite: {
                file: filePath,
                line: node.getStartLineNumber(),
                column: node.getStartLinePos(),
              },
              argumentsProvided: callInfo.arguments,
              expectedProperties: expectedProps,
            });
          }
        }
      });
    
      return schemas;
    }
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states what the tool does but lacks details on traits like whether it's read-only or destructive, output format (e.g., logs, reports), error handling, or performance implications (e.g., speed, resource usage). This leaves significant gaps in understanding how the tool behaves beyond its basic function.

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, clear sentence that efficiently conveys the core purpose without any wasted words. It's front-loaded with the essential information, making it easy to parse and understand quickly, which is ideal for conciseness.

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 complexity of tracing tool usage and the lack of annotations and output schema, the description is insufficiently complete. It doesn't explain what 'trace' entails (e.g., logging calls, analyzing dependencies), what the output looks like, or any behavioral nuances. For a tool with no structured support, more descriptive context is needed to guide effective use.

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 input schema has 100% description coverage, with 'filePath' clearly documented as 'Path to a TypeScript file'. The description adds no additional parameter semantics beyond this, such as file format constraints or path validation rules. Given the high schema coverage, a baseline score of 3 is appropriate as the schema handles 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 ('Trace') and resource ('MCP tool usage in a single TypeScript file'), making it immediately understandable. However, it doesn't explicitly differentiate from sibling tools like 'trace_usage' or 'extract_file', which could have overlapping functionality, preventing a perfect score.

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. It doesn't mention prerequisites, context (e.g., debugging vs. analysis), or comparisons to siblings like 'trace_usage' or 'extract_file', leaving the agent to infer usage scenarios without explicit direction.

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/Mnehmos/trace-mcp'

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