Skip to main content
Glama
dnic-dev

bw-modeling-mcp

by dnic-dev
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

bw_get_process_chain_run_detail

Retrieve process chain run details—steps, statuses, timestamps, message logs—to diagnose failed runs and inspect errors with message variables and source locations.

Instructions

Read the execution detail of one process chain run — all process steps with type, variant, status, timestamps, and parent/child relationships (predecessor graph edges), plus the full message log. chain_id and log_id come from bw_list_process_chain_runs or bw_list_process_chain_last_status output. Use this to diagnose a failed run. Errors come with their message number and long text (diagnosis, system response, procedure). For every failed step the step log is read as well: each error with its message variables and, for a runtime error in a routine, the class, method and line it was raised at — the actual cause when a transformation caught the error and left no short dump.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
log_idYesRun log ID from bw_list_process_chain_runs or bw_list_process_chain_last_status (logId field).
chain_idYesProcess chain technical name (e.g. "CHAIN_NAME").
include_warningsNoAlso show long text, variables and program location for warnings, not only for errors (default false).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.8.1
    • addedInput schema / properties / include_warnings
      Added value: +{
+  "description": "Also show long text, variables and program location for warnings, not only for errors (default false).",
+  "type": "boolean"
+}
  2. Addedv0.9.1

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does substantial work: it discloses that step logs are read for every failed step, that errors carry message number, long text, diagnosis/system response/procedure, and that runtime errors expose class/method/line. It does not state read-only/no-side-effect behavior or output volume limits, which is the remaining gap.

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?

Purpose and scope are front-loaded in the first sentence, with the diagnostic rationale and return detail following. The paragraph is dense but nearly every clause adds distinct information; only the trailing clause about routine class/method/line is slightly verbose.

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?

No output schema exists, and the description compensates by describing the returned step structure and the error/log payload in detail, which is what an agent needs to interpret results. It omits any note on result size or pagination for what is likely a large log payload.

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 all three parameters (log_id, chain_id, include_warnings) are already documented with sources and defaults. The description reinforces the include_warnings semantics ('long text, variables and program location for warnings, not only for errors') but adds no format or syntax detail beyond the schema, so baseline 3 applies.

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?

Opens with a specific verb+resource: 'Read the execution detail of one process chain run' and enumerates exactly what is returned (steps with type, variant, status, timestamps, predecessor edges, plus the full message log). It also distinguishes itself from the sibling list tools by naming where chain_id and log_id originate.

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?

Explicitly states the use case ('Use this to diagnose a failed run') and routes the agent to bw_list_process_chain_runs / bw_list_process_chain_last_status as the ID sources. It stops short of stating when NOT to use it (e.g., for reading chain definitions, which a sibling likely covers).

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

Deploy Server

Other Tools