Skip to main content
Glama
javerthl

ServiceNow MCP Server

by javerthl

submit_change_for_approval

Submit a change request for approval in ServiceNow by providing the change ID and optional comments to initiate the approval workflow.

Instructions

Submit a change request for approval

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
approval_commentsNoComments for the approval request
change_idYesChange request ID or sys_id

Implementation Reference

  • The main handler function that implements the logic for submitting a change request for approval. It validates parameters, updates the change request state to 'assess', creates an approval record in sysapproval_approver table, and returns success or error.
    def submit_change_for_approval(
        auth_manager: AuthManager,
        server_config: ServerConfig,
        params: Dict[str, Any],
    ) -> Dict[str, Any]:
        """
        Submit a change request for approval in ServiceNow.
    
        Args:
            auth_manager: The authentication manager.
            server_config: The server configuration.
            params: The parameters for submitting a change request for approval.
    
        Returns:
            The result of the submission.
        """
        # Unwrap and validate parameters
        result = _unwrap_and_validate_params(
            params, 
            SubmitChangeForApprovalParams,
            required_fields=["change_id"]
        )
        
        if not result["success"]:
            return result
        
        validated_params = result["params"]
        
        # Prepare the request data
        data = {
            "state": "assess",  # Set state to "assess" to submit for approval
        }
        
        # Add approval comments if provided
        if validated_params.approval_comments:
            data["work_notes"] = validated_params.approval_comments
        
        # 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",
            }
        
        # Add Content-Type header
        headers["Content-Type"] = "application/json"
        
        # Make the API request
        url = f"{instance_url}/api/now/table/change_request/{validated_params.change_id}"
        
        try:
            response = requests.patch(url, json=data, headers=headers)
            response.raise_for_status()
            
            # Now, create an approval request
            approval_url = f"{instance_url}/api/now/table/sysapproval_approver"
            approval_data = {
                "document_id": validated_params.change_id,
                "source_table": "change_request",
                "state": "requested",
            }
            
            approval_response = requests.post(approval_url, json=approval_data, headers=headers)
            approval_response.raise_for_status()
            
            approval_result = approval_response.json()
            
            return {
                "success": True,
                "message": "Change request submitted for approval successfully",
                "approval": approval_result["result"],
            }
        except requests.exceptions.RequestException as e:
            logger.error(f"Error submitting change for approval: {e}")
            return {
                "success": False,
                "message": f"Error submitting change for approval: {str(e)}",
            }
  • Pydantic model defining the input parameters for the submit_change_for_approval tool: change_id (required) and approval_comments (optional).
    class SubmitChangeForApprovalParams(BaseModel):
        """Parameters for submitting a change request for approval."""
    
        change_id: str = Field(..., description="Change request ID or sys_id")
        approval_comments: Optional[str] = Field(None, description="Comments for the approval request")
  • Registration of the tool in the get_tool_definitions dictionary, mapping the tool name to its handler function (aliased), schema, return type, description, and serialization method.
    "submit_change_for_approval": (
        submit_change_for_approval_tool,
        SubmitChangeForApprovalParams,
        str,
        "Submit a change request for approval",
        "str",  # Tool returns simple message
    ),
  • Import of the submit_change_for_approval function from change_tools.py into the tools package __init__.
    submit_change_for_approval,
  • Inclusion of 'submit_change_for_approval' in the __all__ list for public export from the tools module.
    "submit_change_for_approval",
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. 'Submit a change request for approval' implies a mutation that may trigger notifications or workflow transitions, but it doesn't specify permissions required, side effects, error conditions, or what happens after submission. For a tool that likely alters system state, this lack of detail is a significant gap.

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?

The description is a single, efficient sentence with no wasted words. It's front-loaded with the core action, though it could benefit from slightly more detail given the tool's likely complexity. There's no fluff or redundancy, making it easy to parse quickly.

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 mutation tool with no annotations and no output schema, the description is insufficient. It doesn't cover behavioral aspects like what the tool returns, error handling, or system impacts. Given the context of change management and numerous sibling tools, more detail is needed to guide effective use.

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%, with clear documentation for both parameters (change_id and approval_comments). The description adds no additional parameter semantics beyond what's in the schema—it doesn't explain format expectations, examples, or how parameters interact. This meets the baseline for high schema coverage but doesn't enhance understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Submit a change request for approval' clearly states the action (submit) and target (change request), but it's somewhat vague about the exact nature of the operation. It doesn't specify whether this initiates an approval workflow, sends notifications, or updates status. While it distinguishes from obvious siblings like 'create_change_request' or 'approve_change', it lacks the specificity needed for a higher score.

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. Given siblings like 'approve_change' and 'reject_change', it's unclear if this is for initial submission, re-submission, or specific workflow states. There's no mention of prerequisites, timing, or context for invocation, leaving the agent to guess based on tool names alone.

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/javerthl/servicenow-mcp'

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