Skip to main content
Glama

natural_language_update

Update ServiceNow records from plain-English instructions, and preview changes with a dry run before applying.

Instructions

Update a record from a plain-English instruction such as "set priority to 2 on INC0010001" (requires 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": {
      "instruction": "<instruction>",
      "table": "<table>"
    },
    "name": "natural_language_update"
  }
}

Input Schema

NameRequiredDescriptionDefault
tableYesTable name
dry_runNoParse and show the update without applying it
instructionYesInstruction naming the record (number or sys_id) and the changes, e.g. "set priority to 2 and state to 2 on INC0010001"

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv5.0.1
    • addedInput schema / properties / dry_run
      Added value: +{
      +  "description": "Parse and show the update without applying it",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / instruction / description
      Previous value: -"Natural language update instruction"New value: +"Instruction naming the record (number or sys_id) and the changes, e.g. \"set priority to 2 and state to 2 on INC0010001\""
  2. First observedv1.0.2

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare the write, non-idempotent, open-world, non-destructive profile, so the description's job is narrower. It contributes a real operational gate (WRITE_ENABLED=true), but leaves undisclosed what happens with an ambiguous instruction, whether multiple matching records can be affected, or whether parsing failures are surfaced as errors.

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?

A single sentence with the core action front-loaded and the environment prerequisite trailing it; nothing is padded. It could carry one more clause of routing guidance without becoming bloated.

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 three-parameter mutation tool with annotations and no output schema, the description covers the action and the write-enable requirement but not the resolution behavior that matters most for natural-language input. An agent could invoke it, yet would not know how ambiguity or partial matches are handled.

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 the schema already explains table, instruction, and dry_run. The description repeats the record-identifier example (number or sys_id) that the instruction property already documents, adding no syntax or constraint information beyond the schema.

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 states a specific verb and resource ("Update a record") and adds the distinguishing modality "from a plain-English instruction," which separates it from the many structured update_* siblings. It stops short of explicitly naming the sibling it replaces (e.g. update_record), so an agent must infer the contrast.

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?

The example instruction gives a concrete usage pattern, and the parenthetical "(requires WRITE_ENABLED=true)" signals a precondition. However, there is no guidance on when to prefer this over the structured update tools, nor any mention of using dry_run to preview before applying.

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