Skip to main content
Glama

sn_mcp_call_tool

Invoke tools on a ServiceNow instance's MCP servers to run Now Assist skills, subflows, actions, Knowledge Graph queries, or scripted REST endpoints. Write tools need WRITE_ENABLED=true.

Instructions

Call a tool on one of the instance's own MCP servers (Now Assist / Otto skills, subflows, actions, Knowledge Graph, scripted REST tools). Runs as the signed-in user and consumes Now Assist entitlement like any MCP call. Tools that ServiceNow does not mark read-only need WRITE_ENABLED=true.

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": {
      "server": "<server>",
      "tool": "<tool>"
    },
    "name": "sn_mcp_call_tool"
  }
}

Input Schema

NameRequiredDescriptionDefault
toolYesTool name from sn_mcp_list_tools
serverYesServer name, e.g. sn_mcp_server_default
argumentsNoTool arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv5.0.1

TDQS

A3.6/5.0
Behavior4/5

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

The annotations already mark it non-read-only, open-world, non-idempotent, non-destructive, and the description adds genuinely new context beyond them: execution identity (signed-in user), entitlement consumption, and the WRITE_ENABLED gate for write-capable target tools. It stops short of describing error propagation or what happens when the wrapped tool fails.

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?

Three tight sentences, front-loading the core action before the operational caveats; no filler. The final sentence is slightly clipped in phrasing but still readable in context.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a generic dispatcher with a polymorphic nested arguments object and no output schema, an agent still lacks guidance on pass-through return shape and failure behavior. The preconditions are well covered, but the dispatch contract is only partially explained.

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 "server" and "tool" are already documented, and the description correctly implies 'tool' must name a tool on that server. The 'arguments' parameter is a free-form nested object whose shape depends entirely on the target tool, and the description does not say that -- its one meaningful 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 ("Call a tool on one of the instance's own MCP servers") and enumerates what counts as a tool there (Now Assist/Otto skills, subflows, actions, Knowledge Graph, scripted REST tools). That distinguishes it from server-management siblings like sn_mcp_create_server or sn_mcp_activate_server, though it never explicitly contrasts itself with them or with calling the underlying capability directly.

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 surfaces real preconditions -- runs as the signed-in user, consumes Now Assist entitlement, and needs WRITE_ENABLED=true for non-read-only tools -- and the tool parameter points at sn_mcp_list_tools. However, there is no explicit statement of when to choose this dispatcher versus a direct/sibling tool, and no when-not guidance.

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