Skip to main content
Glama
sap-s4-mcp

sap-s4-mcp

by Inderj1

propose_delivery_block

Propose a delivery block on a sales order for human approval; no SAP changes occur until the proposal is approved, and the proposal ID is returned.

Instructions

Propose putting a delivery block on a sales order.

Nothing changes in SAP until a person approves the proposal with sap-s4-mcp approve <id>. Returns the proposal id.

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": {
      "sales_order": "<sales_order>",
      "block_reason_code": "<block_reason_code>",
      "reason": "<reason>"
    },
    "name": "propose_delivery_block"
  }
}

Input Schema

NameRequiredDescriptionDefault
reasonYes
sales_orderYes
block_reason_codeYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior5/5

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

The annotations only say readOnly=false and destructive=false, which leaves ambiguous whether the call actually changes SAP. The description resolves that ambiguity precisely: 'Nothing changes in SAP until a person approves the proposal' and it names the approval command. That two-phase, human-gated effect is exactly the behavioral context an agent needs before calling.

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?

Two short sentences, each earning its place: one states the action, the other states the effect and return value. The most important constraint, namely that nothing changes until approval, is placed prominently.

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?

The description covers the deferred-effect model and the return value (proposal id), which matters because there is no output schema. What it does not cover is parameter meaning, especially valid reason codes, and edge cases such as re-proposing on an already-blocked order. That is a real but secondary gap for a 3-parameter tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All three parameters (sales_order, block_reason_code, reason) have 0% schema description coverage and are all required, but the description does not explain any of them. In particular, it gives no guidance on what block_reason_code values are valid or how reason differs from the code, so it does not make up for the schema gap.

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 and resource: 'Propose putting a delivery block on a sales order.' That is more precise than the tool name alone because it says what is being proposed and on what object. It does not explicitly compare itself with siblings, but the 'propose' verb is distinctive enough to separate it from the read-only get_/list_ siblings.

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 scope of the tool is implied: you use it to request a delivery block. However, the description never states when to prefer this over direct action or what prerequisites must be met, such as whether the sales order exists or is already blocked. It describes the approval workflow but not the decision criteria for invoking the tool.

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