Skip to main content
Glama
abap-adt-mcp-gateway
by lusmjs

GatewayCallTool

Invoke any allowed SAP ABAP ADT operation by name on a selected system, passing its declared arguments; receive schema details or an actionable refusal when arguments or system mode do not match.

Instructions

Call any tool of the contract by name. Arguments are the tool's own arguments; system selects the SAP system. Not every name is allowed on every system — a refusal names the mode and the mode that would accept it. If the arguments do not match the tool's schema, the answer carries the schema, not only an error.

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": {
      "tool": "<tool>"
    },
    "name": "GatewayCallTool"
  }
}

Input Schema

NameRequiredDescriptionDefault
toolYesExact tool name from the contract, e.g. GetProgram.
systemNoSAP system to use ((none configured)).
argumentsNoArguments for that tool, exactly as its schema declares (without `system`).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.8/5.0
Behavior4/5

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

Beyond the annotations it discloses two useful failure modes: refusals are permission/mode-based and echo the mode that would accept the call, and argument-schema mismatches return the schema rather than a bare error. This meaningfully reduces trial-and-error. It does not warn that the enum spans destructive operations (Delete*, Unlock*, Update*) despite destructiveHint=false on the wrapper, which is a gap an agent dispatching writes should know about.

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?

Four short sentences that are front-loaded with the core action and spend their remainder only on non-obvious behaviors (system selection, permission refusals, schema echo on mismatch). Nothing is redundant with the schema or padding.

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 dispatcher over a large enum with nested passthrough arguments, the definition covers naming, system scoping, and the two realistic error paths. The main omission is the success contract: it never states that on success the response is the underlying tool's own result payload, which matters because there is no output schema.

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 enum, the `system` string, and the passthrough `arguments` object are already documented. The description mostly restates that `arguments` are the target tool's own arguments and that `system` selects the SAP system; it adds only the nuance that `system` is excluded from the inner argument bag.

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 gives a specific verb (call) and a precise resource (any tool of the contract, addressed by name), making clear this is a generic dispatcher/multiplexer rather than a concrete operation. It does not name the sibling list tools (GatewayListTools, GatewayListSystems) as discovery alternatives, so the differentiation is inferable from the verb rather than stated.

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?

It gives real usage context: the tool name must be an exact contract name, `system` picks the SAP system, and permission varies per system so a refusal is possible. What it does not say is when to reach for this wrapper versus discovering tools first via the sibling list tools, or how the caller should handle a `mode` refusal (retry on another system vs abandon).

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