Skip to main content
Glama
dnic-dev

bw-modeling-mcp

by dnic-dev

bw_append_process_chain_dtp

Add a DTP load step (optionally with DSO activation) to an existing BW process chain, placing it in series before or after a target step or appending it in parallel. Automatically manages edges and chain activation.

Instructions

Add one DTP load step (optionally followed by its own DSO activation step) to an existing Process Chain (RSPC), via the BW/4HANA Cockpit REST API. In-place edit: reads the current model, inserts the node(s)/edge(s)/inline variant, and PUTs it back — the caller does not supply the full model. Positioning: pass "before" to place the block IN SERIES ahead of an existing step (the target's incoming edges are rerouted into the block, then the block links to the target), or "after" to place it in series between a step and its successors. With neither, the block is only APPENDED behind the strand end closest to the trigger (or behind "predecessor") — the target keeps its existing successors, so the block ends up running in PARALLEL to them, not ahead of them. Use before/after whenever the new step must complete before an existing one starts. When adsoact is given, the whole DTP → activation block is placed as one unit. edge_mode defaults to "both", which adds an on-success AND an on-error edge per link ("always continue" — the successor runs even after a failed load). Pass "success_only" for an on-success edge only, which is what a chain whose existing DTP steps have no error edge expects. Idempotent: if the DTP is already a node in the chain, it is skipped without writing. Optionally activates afterwards and then verifies that no collector was inserted and no extra strand appeared. A 412 on the PUT means the ETag was stale (chain modified between read and write); the error reports this explicitly.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dtpYesDTP variant name to append (e.g. "DTP_NAME").
nameYesProcess chain technical name (e.g. "CHAIN_NAME"). Case-insensitive.
afterNoInsert the block IN SERIES AFTER this node — it runs between the target and its former successors. Mutually exclusive with "before".
beforeNoInsert the block IN SERIES BEFORE this node: the target's incoming edges are rerouted into the block, then the block links to the target. Node reference — see the note below. Mutually exclusive with "after".
adsoactNoOptional aDSO name (e.g. "ADSO_NAME"). When given, an ADSOACT step activating this aDSO is added right after the DTP (per-DTP activation) and the two form one block that is placed together.
activateNoIf true, activate the chain immediately after the edit. Default false.
edge_modeNo"both" (default): add an on-success AND an on-error edge per link, so the successor runs even after a failed load ("always continue"). "success_only": add only the on-success edge. Match whatever the chain's existing steps use — the default adds an error edge that a success-only chain does not have.
predecessorNoUsed only when neither before nor after is given. Node to APPEND behind, or the literal "strand_end_auto" (default = terminal node closest to the trigger, ties → first). An append leaves the target's existing successors untouched, so the new block runs in parallel to them — pass before/after instead when it must run in sequence. Node reference forms (same for before / after / predecessor): a DTP or process-variant name; an aDSO held by an ADSOACT/ADSOREM node; the program of an ABAP step, or "PROGRAM/VARIANT"; "TRIGGER" or a collector type ("AND"/"OR"); or "#<index>" using the step numbers printed by bw_get_process_chain. An ambiguous name is rejected with the candidates listed — use "#<index>" then.
transport_requestNoOptional transport request to record the change into. Only relevant when the chain is in a transportable package (not $TMP). If the chain is transportable and exactly one request is available, it is chosen automatically; pass this to disambiguate when several are available. Ignored for $TMP (local) chains.
Behavior5/5

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

With no annotations to rely on, the description fully carries the burden and does so thoroughly: it discloses the in-place read/modify/write behavior, ETag staleness producing a 412, idempotent skip when the DTP already exists, default dual-edge 'always continue' semantics, placement after verification, and the exact structural impact of append vs before/after. This is rich, non-obvious behavioral context well beyond just saying 'adds a step'.

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?

The text is long and dense, but nearly every sentence carries a distinct piece of operational guidance: position routing, edge default, idempotency, ETag failure, block placement. The main structural weakness is that many separate topics are blended together without breaks, so an agent must parse deeply, though no filler is present.

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 tool's complexity (nine parameters, two required), no annotations, and no output schema, this description is remarkably complete. It covers the risky positioning semantics, default behaviors, failure mode for stale ETags, transport relevance, idempotency, and node reference forms, leaving an agent with the information needed to correctly invoke it and interpret unexpected results.

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

Parameters5/5

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

Even though schema coverage is 100%, the description adds substantial semantic meaning: it explains how before/after interacts conceptually with rerouting, what 'neither' means for predecessor/strand end auto-selection, how adsoact makes the DTP and activation one block, and what edge_mode defaults and alternatives actually cause. The node-reference forms for predecessor and sibling named tools like bw_get_process_chain greatly enrich the raw parameter definitions.

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?

The description opens with a specific verb-resource pair: 'Add one DTP load step (optionally followed by its own DSO activation step) to an existing Process Chain (RSPC)'. It clearly differentiates this tool from siblings like bw_swap_process_chain_dtp, bw_add_process_chain_program, and bw_add_process_chain_edge by naming the exact operation and its optional companion step.

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

Usage Guidelines5/5

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

The description gives explicit when-to and when-not-to instructions: use before/after when a step must complete before an existing one, and phrases like 'pass "before" to place...' and 'the block ends up running in PARALLEL to them, not ahead of them' spell out consequences. It also explains that edge_mode 'success_only' is what a chain with no existing error edges expects, giving actionable context for choosing parameters.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/dnic-dev/bw-modeling-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server