Skip to main content
Glama

ABAP Debug Step

abap_debug_step
Destructive

Execute a debugger step in an active ABAP session and return the new position as JSON, supporting step into/over/return, continue to breakpoint, or terminate the debuggee.

Instructions

Execute one debugger step in the active session and return the new position as JSON. stepInto, stepOver and stepReturn move one step; stepContinue runs on to the next breakpoint or to the end; terminateDebuggee ends the debugged program. Needs a debuggee stopped at a breakpoint, which abap_debug_session with action listen delivers. Changes the running program's state, so it cannot be undone.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "stepType": "<stepType>"
    },
    "name": "abap_debug_step"
  }
}

Input Schema

NameRequiredDescriptionDefault
stepTypeYesstepInto (F5): enter the called routine; stepOver (F6): next statement; stepReturn (F7): run to the end of the current routine; stepContinue (F8): run to the next breakpoint; terminateDebuggee: end the program
connectionIdNoSAP system connection ID

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.16.2
    • changedInput schema / properties / stepType / description
      Previous value: -"Step type: stepInto (F5), stepOver (F6), stepReturn (F7), stepContinue (F8), terminateDebuggee"New value: +"stepInto (F5): enter the called routine; stepOver (F6): next statement; stepReturn (F7): run to the end of the current routine; stepContinue (F8): run to the next breakpoint; terminateDebuggee: end the program"
  2. First observedv1.16.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false. The description adds useful context by stating that the change cannot be undone, that a stopped debuggee is required, and that the tool returns the new position as JSON.

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 front-loaded with the core action and return value, then covers step semantics, prerequisites, and state effects in compact sentences. Every sentence contributes relevant information without repetition.

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

Completeness5/5

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

Given the destructive debugger mutation, complete schema coverage, and absence of an output schema, the description supplies the key missing context: the return value, the breakpoint prerequisite, and the irreversible state change. It is complete enough for an agent to invoke the tool correctly.

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 carries the parameter details, including the stepType enum descriptions. The description restates the step meanings and adds only light grouping around the first three modes, without adding connectionId semantics.

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?

States a specific verb and resource: execute one debugger step in the active session and return the new position as JSON. It clearly distinguishes the step variants, so an agent can select it apart from sibling tools such as abap_debug_session.

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

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explains the prerequisite that a debuggee must be stopped at a breakpoint and names abap_debug_session with action listen as the way to reach that state. It also describes when each stepType applies, though it does not explicitly state when not to use this tool or name alternative tools for other debugging actions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.