Skip to main content
Glama
servicenow-mcp

servicenow-mcp

sn_plan_change

Plans a ServiceNow record change or creation without writing it, capturing before/after values and dictionary warnings so users can review and fix the plan before applying.

Instructions

Propose a change to one record without writing it. Give sys_id to change an existing record, or leave it out to plan a new one. The server reads the current values, saves a plan with the before and after value of every field, and returns it with a plan_id. Only reads reach ServiceNow. It also checks each value against the dictionary (choice lists, references, whole numbers, true or false, length, read only, and for a new record unknown and mandatory columns) and returns what it finds as warnings, so a plan can be fixed before anyone reviews it. Give reference fields as sys_ids and choice fields as stored values, the form sn_table_get returns, so the plan compares like with like. Show the changes to the user and call sn_apply_plan only after they agree.

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": {
      "table": "<table>",
      "record": "<record>"
    },
    "name": "sn_plan_change"
  }
}

Input Schema

NameRequiredDescriptionDefault
tableYesTable name, lowercase letters, digits and underscores only. Example: incident.
reasonNoWhy the change is made. Kept in the plan for whoever reviews it.
recordYesField names and the values they should have. Example: {"state": "2", "assigned_to": "<sys_id of the user>"}.
sys_idNoThe sys_id of the record to change: 32 hex characters. Leave out to plan a new record.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description adds much more, notably that only reads reach ServiceNow, that a plan is persisted with before/after values and a plan_id, and that dictionary validation surfaces warnings rather than blocking. The gap is that it never says what happens to a saved plan that is never applied (expiry, cleanup), which matters for a state-creating tool. No contradiction with annotations — 'without writing it' is consistent with destructiveHint=false.

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 purpose and the sys_id branch, and most sentences carry operational weight. It runs slightly long, with the dictionary-check enumeration reading like a list that could be compressed, but nothing is genuinely redundant.

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?

There is no output schema, and the description compensates by describing the return completely: a plan with before/after values for every field, a plan_id, and validation warnings. Combined with the sibling sequencing rule, an agent has everything needed to call it and use the result.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3, but the description adds real meaning about value format: references as sys_ids and choices as stored values, matching what sn_table_get returns. That constraint is not obvious from the schema and prevents malformed plans; the 'reason' parameter is left to the schema, which is fine.

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 opening sentence gives a specific verb and resource ('Propose a change to one record') plus the key scoping fact 'without writing it', which immediately separates it from sn_table_update and sn_apply_plan. A reader knows exactly what the tool produces (a saved plan) before reaching the schema.

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?

It gives a concrete branching rule for sys_id (present = existing record, absent = new record) and an explicit sequencing constraint: 'Show the changes to the user and call sn_apply_plan only after they agree.' That routes the agent to the correct sibling and states the precondition for doing so, leaving little to inference.

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