Skip to main content
Glama
JLKmach

ServiceNow MCP Server

by JLKmach

reject_change

Reject a ServiceNow change request by providing a change ID and rejection reason to prevent implementation of unwanted modifications.

Instructions

Reject a change request

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
change_idYesChange request ID or sys_id
approver_idNoID of the approver
rejection_reasonYesReason for rejection

Implementation Reference

  • The main handler function implementing the reject_change tool. It validates parameters using RejectChangeParams, finds the approval record, updates it to rejected state with reason, and sets the change request state to canceled with work notes.
    def reject_change(
        auth_manager: AuthManager,
        server_config: ServerConfig,
        params: Dict[str, Any],
    ) -> Dict[str, Any]:
        """
        Reject a change request in ServiceNow.
    
        Args:
            auth_manager: The authentication manager.
            server_config: The server configuration.
            params: The parameters for rejecting a change request.
    
        Returns:
            The result of the rejection.
        """
        # Unwrap and validate parameters
        result = _unwrap_and_validate_params(
            params, 
            RejectChangeParams,
            required_fields=["change_id", "rejection_reason"]
        )
        
        if not result["success"]:
            return result
        
        validated_params = result["params"]
        
        # Get the instance URL
        instance_url = _get_instance_url(auth_manager, server_config)
        if not instance_url:
            return {
                "success": False,
                "message": "Cannot find instance_url in either server_config or auth_manager",
            }
        
        # Get the headers
        headers = _get_headers(auth_manager, server_config)
        if not headers:
            return {
                "success": False,
                "message": "Cannot find get_headers method in either auth_manager or server_config",
            }
        
        # First, find the approval record
        approval_query_url = f"{instance_url}/api/now/table/sysapproval_approver"
        
        query_params = {
            "sysparm_query": f"document_id={validated_params.change_id}",
            "sysparm_limit": 1,
        }
        
        try:
            approval_response = requests.get(approval_query_url, headers=headers, params=query_params)
            approval_response.raise_for_status()
            
            approval_result = approval_response.json()
            
            if not approval_result.get("result") or len(approval_result["result"]) == 0:
                return {
                    "success": False,
                    "message": "No approval record found for this change request",
                }
            
            approval_id = approval_result["result"][0]["sys_id"]
            
            # Now, update the approval record to rejected
            approval_update_url = f"{instance_url}/api/now/table/sysapproval_approver/{approval_id}"
            headers["Content-Type"] = "application/json"
            
            approval_data = {
                "state": "rejected",
                "comments": validated_params.rejection_reason,
            }
            
            approval_update_response = requests.patch(approval_update_url, json=approval_data, headers=headers)
            approval_update_response.raise_for_status()
            
            # Finally, update the change request state to "canceled"
            change_url = f"{instance_url}/api/now/table/change_request/{validated_params.change_id}"
            
            change_data = {
                "state": "canceled",  # This may vary depending on ServiceNow configuration
                "work_notes": f"Change request rejected: {validated_params.rejection_reason}",
            }
            
            change_response = requests.patch(change_url, json=change_data, headers=headers)
            change_response.raise_for_status()
            
            return {
                "success": True,
                "message": "Change request rejected successfully",
            }
        except requests.exceptions.RequestException as e:
            logger.error(f"Error rejecting change: {e}")
            return {
                "success": False,
                "message": f"Error rejecting change: {str(e)}",
            } 
  • Pydantic BaseModel defining the input schema for the reject_change tool, including required change_id and rejection_reason, optional approver_id.
    class RejectChangeParams(BaseModel):
        """Parameters for rejecting a change request."""
    
        change_id: str = Field(..., description="Change request ID or sys_id")
        approver_id: Optional[str] = Field(None, description="ID of the approver")
        rejection_reason: str = Field(..., description="Reason for rejection")
  • Tool registration in the central tool_definitions dictionary used by the MCP server, associating the tool name with its handler function (aliased), params schema, return type hint, description, and serialization method.
    "reject_change": (
        reject_change_tool,
        RejectChangeParams,
        str,
        "Reject a change request",
        "str",  # Tool returns simple message
    ),
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. 'Reject' implies a destructive write operation, but the description doesn't mention permissions required, whether rejection is reversible, what happens to the change request status, or any side effects. This leaves significant behavioral gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence with zero wasted words. It's appropriately sized for a simple action and front-loads the essential information.

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

Completeness2/5

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

For a destructive mutation tool with no annotations and no output schema, the description is inadequate. It doesn't explain what rejection entails, what the expected outcome is, or any behavioral constraints. Given the complexity of change management workflows, more context is needed.

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 documents all three parameters thoroughly. The description adds no additional parameter context beyond what's in the schema, meeting the baseline expectation but not exceeding it.

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 'Reject a change request' clearly states the action (reject) and target resource (change request). It's specific enough to understand the basic function, though it doesn't differentiate from sibling tools like 'approve_change' beyond the opposite action.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., change must be in pending approval state), exclusions, or relationships with sibling tools like 'approve_change' or 'update_change_request'.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/JLKmach/servicenow-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server