mcp-abap-adt

UpdateBehaviorImplementation

Updates the source code of an existing ABAP behavior implementation class, including lock, write, unlock, and optional activation.

Instructions

Update source code of an existing ABAP behavior implementation class. Updates the implementations include. Manages lock, update, unlock, and optional activation. Runs outside batch mode.

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": {
      "class_name": "<class_name>",
      "behavior_definition": "<behavior_definition>",
      "implementation_code": "<implementation_code>"
    },
    "name": "UpdateBehaviorImplementation"
  }
}

Input Schema

Name	Required	Description	Default
`detail`	No	How much of the answer to return: "terse" (default, the fields you need to act), "full" (the whole parse), "raw" (the document as ADT sent it).	terse
`activate`	No	Activate behavior implementation after update. Default: true.
`class_name`	Yes	Behavior Implementation class name. Must exist in the system.
`transport_request`	No	Transport request number, not a task. Optional if object is local or already in transport.
`behavior_definition`	Yes	Referenced Behavior Definition name. Accepted for compatibility; not forwarded to the write — the shipped update() no longer reads it (it writes the implementations include only, never the FOR BEHAVIOR OF main source).
`implementation_code`	Yes	Implementation code for the implementations include. Contains the actual behavior implementation methods.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv16.0.0Oct 4, 2026

changedInput schema / properties / behavior_definition / description

Previous value: -"Behavior Definition name (e.g., ZI_MY_ENTITY). Must match the behavior definition used when creating the class."New value: +"Referenced Behavior Definition name. Accepted for compatibility; not forwarded to the write — the shipped update() no longer reads it (it writes the implementations include only, never the FOR BEHAVIOR OF main source)."

changedInput schema / properties / class_name / description

Previous value: -"Behavior Implementation class name (e.g., ZBP_MY_ENTITY). Must exist in the system."New value: +"Behavior Implementation class name. Must exist in the system."

addedInput schema / properties / detail

Added value: +{
+  "default": "terse",
+  "description": "How much of the answer to return: \"terse\" (default, the fields you need to act), \"full\" (the whole parse), \"raw\" (the document as ADT sent it).",
+  "enum": [
+    "terse",
+    "full",
+    "raw"
+  ],
+  "type": "string"
+}

changedInput schema / properties / transport_request / description

Previous value: -"Transport request number (e.g., E19K905635). Optional if object is local or already in transport."New value: +"Transport request number, not a task. Optional if object is local or already in transport."

First observedDec 29, 2025

TDQS

B3.4/5.0

Behavior3/5

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

With no annotations, the description carries the full burden and does disclose something valuable: it manages lock/update/unlock, activation is optional, and it cannot run in batch mode. It does not say whether the implementations include is fully replaced or merged, what happens on lock failure, or whether a transport is mandatory — all material for an unannotated write tool.

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?

Four short, front-loaded sentences with no filler; the target of the write is stated first. 'Updates the implementations include' is mildly redundant with sentence one but earns its place by scoping the write.

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?

Six parameters, no annotations, no output schema, so the burden is on the description. It covers scope, locking, activation and batch restriction, but leaves overwrite semantics and any indication of what the caller gets back unstated — a gap for a mutation tool.

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 every parameter including the behavioral quirks (behavior_definition accepted but not forwarded, transport_request must be a request not a task, activate defaults true) is already documented in the schema. The description adds no parameter-level meaning beyond 'Updates the implementations include.'

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?

Names a specific verb and resource: 'Update source code of an existing ABAP behavior implementation class,' and narrows it to the implementations include. This distinguishes it from UpdateBehaviorDefinition and CreateBehaviorImplementation without needing to name them, though no sibling is explicitly called out.

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

Usage Guidelines3/5

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

The line 'Runs outside batch mode' gives a real operating constraint, and 'existing' implies CreateBehaviorImplementation is not the tool to use. But there is no explicit when-to-use vs. when-not, and no pointer to ActivateBehaviorImplementation or CheckClass for validation.

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

Deploy Server