Skip to main content
Glama

trace_usage

Analyze how client code interacts with MCP tools by identifying callTool() invocations and tracking property access on results to detect schema mismatches.

Instructions

Trace how client code uses MCP tools. Finds callTool() invocations and tracks which properties are accessed on results.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
rootDirYesRoot directory of consumer source code
includeNoGlob patterns to include
excludeNoGlob patterns to exclude

Implementation Reference

  • MCP tool handler for 'trace_usage': parses input with TraceUsageInput schema, invokes traceConsumerUsage on the consumer directory, logs progress, and returns JSON with traced usage data.
    case 'trace_usage': {
      const input = TraceUsageInput.parse(args);
      log(`Tracing usage in: ${input.rootDir}`);
      
      const usage = await traceConsumerUsage({
        rootDir: input.rootDir,
        include: input.include,
        exclude: input.exclude,
      });
      
      log(`Found ${usage.length} tool calls`);
      
      return {
        content: [
          {
            type: 'text',
            text: JSON.stringify({
              success: true,
              count: usage.length,
              usage,
            }, null, 2),
          },
        ],
      };
    }
  • Zod input schema for the trace_usage tool, defining rootDir (required), include/exclude globs (optional).
    const TraceUsageInput = z.object({
      rootDir: z.string().describe('Root directory of consumer/client source code'),
      include: z.array(z.string()).optional().describe('Glob patterns to include'),
      exclude: z.array(z.string()).optional().describe('Glob patterns to exclude'),
    });
  • src/index.ts:155-166 (registration)
    Registration of 'trace_usage' tool in the MCP server's listTools response, including name, description, and inputSchema.
      name: 'trace_usage',
      description: 'Trace how client code uses MCP tools. Finds callTool() invocations and tracks which properties are accessed on results.',
      inputSchema: {
        type: 'object',
        properties: {
          rootDir: { type: 'string', description: 'Root directory of consumer source code' },
          include: { type: 'array', items: { type: 'string' }, description: 'Glob patterns to include' },
          exclude: { type: 'array', items: { type: 'string' }, description: 'Glob patterns to exclude' },
        },
        required: ['rootDir'],
      },
    },
  • Core helper function traceConsumerUsage invoked by the handler; selects language parser (default: typescript) and delegates to parser.traceUsage for actual tracing logic.
    export async function traceConsumerUsage(
      options: TracerOptions
    ): Promise<ConsumerSchema[]> {
      // For backward compatibility, default to TypeScript
      const language = options.language || 'typescript';
    
      // Get parser from registry
      if (!hasParser(language)) {
        throw new Error(
          `No parser available for language: ${language}. Make sure to call bootstrapLanguageParsers() at startup.`
        );
      }
    
      const parser = getParser(language);
    
      return parser.traceUsage({
        rootDir: options.rootDir,
        callPatterns: options.callPatterns,
        include: options.include,
        exclude: options.exclude,
      });
    }
Behavior2/5

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

With no annotations provided, the description carries full burden but lacks behavioral details. It doesn't disclose whether this is a read-only analysis tool, what permissions are needed, how results are returned, or any performance implications. The description explains the analysis goal but not the operational behavior.

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 perfectly concise with two clear sentences that each earn their place. The first sentence states the overall purpose, and the second provides specific technical details about what it finds and tracks.

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?

For a tool with 3 parameters, no annotations, and no output schema, the description is incomplete. It explains what the tool analyzes but doesn't cover how results are returned, what format they take, or any behavioral constraints. The agent would need to guess about the output and operational characteristics.

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 description coverage is 100%, so the schema already documents all three parameters thoroughly. The description adds no additional parameter context beyond what's in the schema, maintaining the baseline score for high schema coverage.

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 specific action ('Trace'), target ('client code uses MCP tools'), and mechanism ('Finds callTool() invocations and tracks which properties are accessed on results'). It distinguishes itself from siblings like trace_file by focusing on tool usage analysis rather than file-level tracing.

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 like trace_file or other siblings. The description explains what it does but offers no context about appropriate scenarios, 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/Mnehmos/trace-mcp'

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