Skip to main content
Glama
workbackai

MCP NodeJS Debugger

by workbackai

delete_breakpoint

Removes a breakpoint by its ID to clean up debugger state during Node.js debugging sessions.

Instructions

Deletes a specified breakpoint

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
breakpointIdYesID of the breakpoint to remove

Implementation Reference

  • The async handler function that executes the delete_breakpoint tool logic. It ensures the debugger is enabled, sends Debugger.removeBreakpoint via the inspector, removes the breakpoint from local tracking (breakpoints Map), and returns a success or error message.
      async ({ breakpointId }) => {
        try {
          // Ensure debugger is enabled
          if (!inspector.debuggerEnabled) {
            await inspector.enableDebugger();
          }
          
          await inspector.send('Debugger.removeBreakpoint', {
            breakpointId: breakpointId
          });
          
          // Remove from our local tracking
          inspector.breakpoints.delete(breakpointId);
          
          return {
            content: [{
              type: "text",
              text: `Breakpoint ${breakpointId} removed`
            }]
          };
        } catch (err) {
          return {
            content: [{
              type: "text",
              text: `Error removing breakpoint: ${err.message}`
            }]
          };
        }
      }
    );
  • Registration of the delete_breakpoint tool via server.tool() with the name 'delete_breakpoint' and a description.
    server.tool(
      "delete_breakpoint",
      "Deletes a specified breakpoint",
      {
        breakpointId: z.string().describe("ID of the breakpoint to remove")
      },
      async ({ breakpointId }) => {
        try {
          // Ensure debugger is enabled
          if (!inspector.debuggerEnabled) {
            await inspector.enableDebugger();
          }
          
          await inspector.send('Debugger.removeBreakpoint', {
            breakpointId: breakpointId
          });
          
          // Remove from our local tracking
          inspector.breakpoints.delete(breakpointId);
          
          return {
            content: [{
              type: "text",
              text: `Breakpoint ${breakpointId} removed`
            }]
          };
        } catch (err) {
          return {
            content: [{
              type: "text",
              text: `Error removing breakpoint: ${err.message}`
            }]
          };
        }
      }
    );
  • Input schema for delete_breakpoint defining breakpointId as a required string validated by Zod.
    {
      breakpointId: z.string().describe("ID of the breakpoint to remove")
    },
  • The Inspector class stores breakpoints in a Map (this.breakpoints) which is used by the delete_breakpoint handler to remove breakpoints from local tracking.
    this.breakpoints = new Map();
    this.paused = false;
    this.currentCallFrames = [];
    this.retryOptions = retryOptions;
Behavior2/5

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

No annotations are provided, so the description carries full burden. It only states 'deletes' without disclosing side effects (e.g., irreversibility), error handling (e.g., missing breakpoint), or permissions. A destructive action warrants more transparency.

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 one sentence with no extraneous text. It is front-loaded with the key action. However, it is too brief to provide complete context, but still acceptable for conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with one parameter, the description plus schema are minimally adequate. However, no output schema is provided, and there is no mention of related tools (e.g., list_breakpoints for ID retrieval) or behavioral traits, making it incomplete but functional.

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 a description for breakpointId, so baseline is 3. The description adds no further meaning; it does not explain how the ID is used or where to obtain it. No improvement over schema.

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 'Deletes a specified breakpoint' clearly indicates the action (delete) and the resource (breakpoint), distinguishing it from siblings like set_breakpoint (add) or list_breakpoints (read). However, it does not explicitly contrast with siblings, so it is not a 5.

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. For example, it does not mention that list_breakpoints can provide valid IDs or that breakpoints must be set before deletion. The context is implied but not explicitly stated.

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/workbackai/mcp-nodejs-debugger'

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