now-sdk-ext-mcp

Create Update Set

create_update_set

Create a new in-progress update set in a specified ServiceNow application; it does not make the set current.

Instructions

Create a new update set, In progress, in the given application. It is not made current: use set_current_update_set for that. IMPORTANT: This creates a new update set on the instance.

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": {
      "name": "<name>",
      "application": "<application>"
    },
    "name": "create_update_set"
  }
}

Input Schema

Name	Required	Description
`name`	Yes	The name of the update set to create (at most 80 characters).
`instance`	No	The 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.
`application`	Yes	Required. The application the set belongs to: global, a sys_scope sys_id, or a scope name that matches exactly one active application (not a display name). Create the set in the application you are changing; the set is checked for a duplicate name there and read back.
`description`	No	Optional single-line description for the update set.

Schema Changelog

Changes observed during successful MCP inspections.

Changed9 schema fields changedv5.5.0Nov 7, 2026

changedInput schema / properties / application / description

Previous value: -"Optional application scope sys_id to associate with the update set."New value: +"Required. The application the set belongs to: global, a sys_scope sys_id, or a scope name that matches exactly one active application (not a display name). Create the set in the application you are changing; the set is checked for a duplicate name there and read back."

addedInput schema / properties / application / pattern

Added value: +"^(global|[0-9a-f]{32}|[a-z0-9_]{1,40})$"

changedInput schema / properties / description / description

Previous value: -"Optional description for the update set."New value: +"Optional single-line description for the update set."

addedInput schema / properties / description / pattern
```
Added value: +"^[^\\p{Cc}]*$"
```

changedInput schema / properties / name / description

Previous value: -"The name of the update set to create."New value: +"The name of the update set to create (at most 80 characters)."

addedInput schema / properties / name / maxLength
```
Added value: +80
```
addedInput schema / properties / name / minLength
```
Added value: +1
```
addedInput schema / properties / name / pattern
```
Added value: +"^[^\\p{Cc}]*$"
```

changedInput schema / required

Previous value: -[
-  "name"
-]New value: +[
+  "name",
+  "application"
+]

First observedv2.5.1May 30, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare the mutation profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=true), so the bar is lower. The description adds non-obvious behavior beyond them: the new set lands in 'In progress' state and is deliberately not made current. It omits permission/auth requirements and any side effects like the duplicate-name check, which the schema mentions instead.

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 short sentences, front-loaded with the create action and the not-current constraint. The trailing 'IMPORTANT: This creates a new update set on the instance' largely restates the verb and the openWorldHint annotation, making it the weakest sentence, but it is not harmful.

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?

For a single-record creation tool with no output schema and full annotation coverage, the description covers effect, target application, and resulting state. The notable remaining gap is the return value—an agent does not learn whether the new set's sys_id or record comes back, which matters for chaining into set_current_update_set.

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 every parameter is already documented in detail, including the application identifier format and instance alias fallback. The description only echoes 'in the given application' and adds no new semantics such as naming constraints or defaults, so the 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?

States a specific verb and resource ('Create a new update set') plus the resulting state ('In progress') and the scope ('in the given application'). It explicitly separates itself from set_current_update_set, so an agent can pick between them without reading either schema.

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?

Gives a clear when-this-instead-of-that rule: creating does not make the set current, and set_current_update_set is named for that step. It does not address related siblings like clone_update_set or when to reuse an existing set, but the critical selection path is covered.

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

Deploy Server