Skip to main content
Glama

step

Execute a single step in Go program debugging to move to the next line or instruction within a debug session.

Instructions

Step into function call

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sessionIdYesID of the debug session

Implementation Reference

  • Executes the 'step' tool by sending a 'step' command to the Delve debugger session via sendDelveCommand and returns a confirmation message.
    case "step": {
      await sendDelveCommand(session, "Command", { name: "step" });
      return {
        content: [{
          type: "text",
          text: "Stepped into function"
        }]
      };
    }
  • Defines the input schema for the 'step' tool, which requires a sessionId parameter.
    name: "step",
    description: "Step into function call",
    inputSchema: {
      type: "object",
      properties: {
        sessionId: {
          type: "string",
          description: "ID of the debug session"
        }
      },
      required: ["sessionId"]
    }
  • src/server.ts:410-413 (registration)
    Registers the 'step' tool (among control tools) by dispatching tool calls to the handleControlCommands function in the MCP CallToolRequestSchema handler.
    // Control commands
    if (["setBreakpoint", "removeBreakpoint", "continue", "next", "step", "stepout", "variables", "evaluate"].includes(name)) {
      return handleControlCommands(name, args);
    }
  • src/server.ts:64-397 (registration)
    Registers the 'step' tool in the list of available tools provided by ListToolsRequestSchema, including its schema.
    server.setRequestHandler(ListToolsRequestSchema, async () => {
      return {
        tools: [
          // Debug tools
          {
            name: "debug",
            description: "Start debugging a Go package",
            inputSchema: {
              type: "object",
              properties: {
                package: {
                  type: "string",
                  description: "Package to debug (defaults to current directory)"
                },
                buildFlags: {
                  type: "string",
                  description: "Build flags to pass to the compiler"
                }
              }
            }
          },
          {
            name: "attach",
            description: "Attach to a running process",
            inputSchema: {
              type: "object",
              properties: {
                pid: {
                  type: "number",
                  description: "Process ID to attach to"
                }
              },
              required: ["pid"]
            }
          },
          {
            name: "exec",
            description: "Debug a precompiled binary",
            inputSchema: {
              type: "object",
              properties: {
                binary: {
                  type: "string",
                  description: "Path to the binary"
                },
                args: {
                  type: "array",
                  items: { type: "string" },
                  description: "Arguments to pass to the binary"
                }
              },
              required: ["binary"]
            }
          },
          {
            name: "test",
            description: "Debug tests in a package",
            inputSchema: {
              type: "object",
              properties: {
                package: {
                  type: "string",
                  description: "Package to test (defaults to current directory)"
                },
                testFlags: {
                  type: "array",
                  items: { type: "string" },
                  description: "Flags to pass to go test"
                }
              }
            }
          },
          // Control tools
          {
            name: "setBreakpoint",
            description: "Set a breakpoint in the debugged program",
            inputSchema: {
              type: "object",
              properties: {
                sessionId: {
                  type: "string",
                  description: "ID of the debug session"
                },
                file: {
                  type: "string",
                  description: "File path where to set the breakpoint"
                },
                line: {
                  type: "number",
                  description: "Line number for the breakpoint"
                },
                condition: {
                  type: "string",
                  description: "Optional condition for the breakpoint"
                }
              },
              required: ["sessionId", "file", "line"]
            }
          },
          {
            name: "removeBreakpoint",
            description: "Remove a breakpoint",
            inputSchema: {
              type: "object",
              properties: {
                sessionId: {
                  type: "string",
                  description: "ID of the debug session"
                },
                breakpointId: {
                  type: "number",
                  description: "ID of the breakpoint to remove"
                }
              },
              required: ["sessionId", "breakpointId"]
            }
          },
          {
            name: "continue",
            description: "Continue program execution",
            inputSchema: {
              type: "object",
              properties: {
                sessionId: {
                  type: "string",
                  description: "ID of the debug session"
                }
              },
              required: ["sessionId"]
            }
          },
          {
            name: "next",
            description: "Step over to next line",
            inputSchema: {
              type: "object",
              properties: {
                sessionId: {
                  type: "string",
                  description: "ID of the debug session"
                }
              },
              required: ["sessionId"]
            }
          },
          {
            name: "step",
            description: "Step into function call",
            inputSchema: {
              type: "object",
              properties: {
                sessionId: {
                  type: "string",
                  description: "ID of the debug session"
                }
              },
              required: ["sessionId"]
            }
          },
          {
            name: "stepout",
            description: "Step out of current function",
            inputSchema: {
              type: "object",
              properties: {
                sessionId: {
                  type: "string",
                  description: "ID of the debug session"
                }
              },
              required: ["sessionId"]
            }
          },
          {
            name: "variables",
            description: "List local variables in current scope",
            inputSchema: {
              type: "object",
              properties: {
                sessionId: {
                  type: "string",
                  description: "ID of the debug session"
                }
              },
              required: ["sessionId"]
            }
          },
          {
            name: "evaluate",
            description: "Evaluate an expression in current scope",
            inputSchema: {
              type: "object",
              properties: {
                sessionId: {
                  type: "string",
                  description: "ID of the debug session"
                },
                expr: {
                  type: "string", 
                  description: "Expression to evaluate"
                }
              },
              required: ["sessionId", "expr"]
            }
          },
          // Advanced debug tools
          {
            name: "core",
            description: "Examine a core dump",
            inputSchema: {
              type: "object",
              properties: {
                executable: {
                  type: "string",
                  description: "Path to the executable that produced the core dump"
                },
                corePath: {
                  type: "string",
                  description: "Path to the core dump file"
                }
              },
              required: ["executable", "corePath"]
            }
          },
          {
            name: "dap",
            description: "Start a DAP (Debug Adapter Protocol) server",
            inputSchema: {
              type: "object",
              properties: {
                clientAddr: {
                  type: "string",
                  description: "Optional address where DAP client is waiting for connection"
                }
              }
            }
          },
          {
            name: "replay",
            description: "Replay an rr trace",
            inputSchema: {
              type: "object",
              properties: {
                tracePath: {
                  type: "string",
                  description: "Path to the rr trace directory"
                },
                onProcess: {
                  type: "number",
                  description: "Optional PID to pass to rr"
                }
              },
              required: ["tracePath"]
            }
          },
          {
            name: "trace",
            description: "Trace program execution",
            inputSchema: {
              type: "object",
              properties: {
                regexp: {
                  type: "string",
                  description: "Regular expression to match functions to trace"
                },
                pkg: {
                  type: "string",
                  description: "Package to trace (defaults to .)"
                },
                ebpf: {
                  type: "boolean",
                  description: "Use eBPF for tracing (experimental)"
                },
                stack: {
                  type: "number",
                  description: "Show stack trace with given depth"
                },
                pid: {
                  type: "number",
                  description: "Pid to attach to"
                }
              },
              required: ["regexp"]
            }
          },
          // Configuration tools
          {
            name: "version",
            description: "Get Delve version information",
            inputSchema: {
              type: "object",
              properties: {}
            }
          },
          {
            name: "setBackend",
            description: "Set the backend for debugging",
            inputSchema: {
              type: "object",
              properties: {
                backend: {
                  type: "string",
                  description: "Backend to use (default, native, lldb, or rr)",
                  enum: ["default", "native", "lldb", "rr"]
                }
              },
              required: ["backend"]
            }
          },
          {
            name: "configureLogging",
            description: "Configure debug logging",
            inputSchema: {
              type: "object",
              properties: {
                components: {
                  type: "array",
                  items: {
                    type: "string",
                    enum: ["debugger", "gdbwire", "lldbout", "debuglineerr", "rpc", "dap", "fncall", "minidump", "stack"]
                  },
                  description: "Components to enable logging for"
                },
                destination: {
                  type: "string",
                  description: "Log destination (file path or file descriptor)"
                }
              },
              required: ["components"]
            }
          }
        ]
      };
    });
Behavior1/5

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

With no annotations provided, the description carries full burden for behavioral disclosure but provides none. It doesn't indicate whether this is a read or write operation, what permissions are needed, what happens to the debug session state, or what the expected outcome is. The phrase 'step into' suggests execution control but lacks essential behavioral details.

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 extremely concise at just three words, which could be appropriate if it were more informative. However, this brevity borders on under-specification rather than effective conciseness. It's front-loaded but lacks substance.

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 debugging tool with no annotations and no output schema, the description is inadequate. It doesn't explain what 'stepping into a function call' means in this context, what the expected behavior is, or what happens after execution. Given the complexity implied by the sibling tools and lack of structured documentation, more context is needed.

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% with the single parameter 'sessionId' well-documented in the schema. The description adds no parameter information beyond what the schema provides, which is acceptable given the high schema coverage. The baseline of 3 is appropriate when the schema does the heavy lifting.

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

Purpose2/5

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

The description 'Step into function call' is a tautology that essentially restates the tool name 'step' without providing meaningful context. While it suggests this is related to debugging/stepping through code, it doesn't specify what resource or system it operates on or distinguish it from sibling tools like 'next', 'continue', or 'stepout'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

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. There are multiple related debugging tools (next, continue, stepout) but no indication of when 'step into function call' is appropriate versus those other stepping/execution control tools.

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/dwisiswant0/delve-mcp'

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