Skip to main content
Glama
Sign In
now-sdk-ext-mcp

now-sdk-ext-mcp

by sonisoft-cnanda
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Start Flow Debug Run

debug_flow_start
Destructive

Starts a ServiceNow Workflow Studio debug run and pauses before the first step, returning the run context ID, stoppable steps, and current location so you can step through or cancel it.

Instructions

Start a Workflow Studio debug run (Test > Debug) of a flow or subflow and leave it paused before its first step. The flow's current draft runs, for real: records it creates or changes are kept, so debug a copy (copy_flow) in a scratch app. Returns the run's root context id, the steps it can stop at, and where it is. Continue with debug_flow_step, and always end it: run it to the end, or debug_flow_cancel. debug_flow_run_to does all of this in one call. Only when the user asked to debug.

Input Schema

NameRequiredDescriptionDefault
flowYesThe flow or subflow: its sys_hub_flow sys_id, or scope.internal_name (e.g. x_app.create_task_copy).
fullNoShow values in full, and the engine's internal outputs (__action_status__ and the like).
inputsNoInputs by name. For a subflow, its declared inputs (checked before anything runs; an array for an array input is sent as Workflow Studio sends it). For a flow, its trigger outputs (e.g. current, table_name).
instanceNoThe ServiceNow instance auth alias to connect to. This is the alias configured via `snc configure` (e.g., "myinstance", "prod", "test"). The user will typically refer to this by name when saying things like "on my myinstance instance". If not provided, falls back to the SN_AUTH_ALIAS environment variable.
breakpointsNoSteps to break at, by the number Workflow Studio shows.
timeout_secondsNoSeconds to wait for the run to pause again or end. Default 45, under the 60-second request timeout many MCP clients use. A client that gives up first leaves the run open: find it with list_flow_debug_sessions.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv5.5.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations flag destructiveHint=true, but the description goes well beyond them: it explains that the flow's current draft runs for real and created/changed records are kept, and recommends debugging a copy via copy_flow in a scratch app. It also discloses the timeout default rationale and the failure mode where a client giving up leaves an orphaned run to find with list_flow_debug_sessions.

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?

Front-loaded with the action and the pause state, then the risk warning, then the lifecycle. Dense but every sentence carries real information; the only slight redundancy is restating the debug_flow_run_to alternative after the cancellation guidance.

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?

No output schema exists, yet the description names the return payload (root context id, stoppable steps, current position) and explains the full lifecycle plus the cleanup obligation. For a destructive, stateful, session-creating tool, nothing an agent needs to call it safely is missing.

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%, so every parameter is already documented in the schema, including flow format, inputs, instance alias, breakpoints, and timeout. The description adds no parameter-level detail beyond what the schema states, so the baseline of 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?

States a specific verb and resource ('Start a Workflow Studio debug run ... of a flow or subflow') and pins down the exact stopping point ('leave it paused before its first step'). It also implicitly distinguishes itself from debug_flow_run_to by naming that sibling as the one-call variant.

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?

Gives explicit routing: use debug_flow_run_to to do the whole thing in one call, continue with debug_flow_step, and terminate with debug_flow_cancel. It also states the gating precondition 'Only when the user asked to debug,' so the agent knows when not to call it.

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