abap-config-mcp

Compare Customizing Between Two Org Units

customizing_diff

Read-onlyIdempotent

Compare customizing table or view rows between two org-unit keys, such as plant 1000 versus 2000, to reveal entries present in the source but missing from the target and vice versa.

Instructions

Compare customizing configuration for a table/view between two org-unit key values (e.g. plant 1000 vs plant 2000, or company code DE01 vs AT01). Shows rows present in source but missing from target, and vice versa. Use customizing_plan_change to generate the insert plan for the missing rows.

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": {
      "objectName": "<objectName>",
      "keyField": "<keyField>",
      "sourceKey": "<sourceKey>",
      "targetKey": "<targetKey>"
    },
    "name": "customizing_diff"
  }
}

Input Schema

Name	Required	Description
`keyField`	Yes	Org-unit key field (e.g. WERKS, BUKRS, VKORG, LGNUM)
`sourceKey`	Yes	Source org-unit value (reference, e.g. '1000')
`targetKey`	Yes	Target org-unit value (e.g. '2000')
`objectName`	Yes	Maintenance view or table name
`connectionId`	No	SAP system connection ID

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.16.0Nov 12, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so safety is largely covered; the description still adds real value by stating the return semantics, namely two sets of rows (present in source but missing from target, and vice versa). It omits any mention of the remote SAP system the call reaches, or how the optional connectionId affects which system is compared.

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?

Three tight sentences: purpose and scope first, then what the result contains, then the next-step handoff. No repetition of the title, no filler, and the most decision-relevant facts are front-loaded.

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

Completeness4/5

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

For a read-only comparison tool with no output schema, the definition covers purpose, inputs by example and result shape well enough to call it confidently. The remaining gap is operational: nothing explains the role of the optional connectionId or how the two org units are resolved against the connection's systems.

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 keyField, sourceKey and targetKey already documented inline including example field names (WERKS, BUKRS, VKORG, LGNUM). The description's plant/company-code examples illustrate the direction from source to target but introduce no semantics, such as whether multiple key fields can be compared at once or what happens if the target value is absent, that the schema does not already provide.

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?

Uses a specific verb ("Compare") against a specific resource ("customizing configuration for a table/view") and scopes it to two org-unit key values. The concrete examples (plant 1000 vs 2000, company code DE01 vs AT01) make the operation immediately recognizable, and it explicitly names the sibling customizing_plan_change as the follow-up rather than a substitute.

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?

It states the triggering scenario (comparing customizing rows across two org-unit values) and hands off explicitly to customizing_plan_change for the next step, which tells the agent where this tool stops. It stops short of any exclusion, e.g. that it does not modify or copy rows and that org_copy or customizing_apply is the tool for actually moving configuration.

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

Deploy Server