Skip to main content
Glama
JLKmach

ServiceNow MCP Server

by JLKmach

resolve_incident

Close ServiceNow incidents by providing resolution codes and notes to document how issues were addressed.

Instructions

Resolve an incident in ServiceNow

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
incident_idYesIncident ID or sys_id
resolution_codeYesResolution code for the incident
resolution_notesYesResolution notes for the incident

Implementation Reference

  • Core handler function that resolves an incident by updating its state to resolved (6) via ServiceNow Table API, handling both sys_id and number lookup.
    def resolve_incident(
        config: ServerConfig,
        auth_manager: AuthManager,
        params: ResolveIncidentParams,
    ) -> IncidentResponse:
        """
        Resolve an incident in ServiceNow.
    
        Args:
            config: Server configuration.
            auth_manager: Authentication manager.
            params: Parameters for resolving the incident.
    
        Returns:
            Response with the result of the operation.
        """
        # Determine if incident_id is a number or sys_id
        incident_id = params.incident_id
        if len(incident_id) == 32 and all(c in "0123456789abcdef" for c in incident_id):
            # This is likely a sys_id
            api_url = f"{config.api_url}/table/incident/{incident_id}"
        else:
            # This is likely an incident number
            # First, we need to get the sys_id
            try:
                query_url = f"{config.api_url}/table/incident"
                query_params = {
                    "sysparm_query": f"number={incident_id}",
                    "sysparm_limit": 1,
                }
    
                response = requests.get(
                    query_url,
                    params=query_params,
                    headers=auth_manager.get_headers(),
                    timeout=config.timeout,
                )
                response.raise_for_status()
    
                result = response.json().get("result", [])
                if not result:
                    return IncidentResponse(
                        success=False,
                        message=f"Incident not found: {incident_id}",
                    )
    
                incident_id = result[0].get("sys_id")
                api_url = f"{config.api_url}/table/incident/{incident_id}"
    
            except requests.RequestException as e:
                logger.error(f"Failed to find incident: {e}")
                return IncidentResponse(
                    success=False,
                    message=f"Failed to find incident: {str(e)}",
                )
    
        # Build request data
        data = {
            "state": "6",  # Resolved
            "close_code": params.resolution_code,
            "close_notes": params.resolution_notes,
            "resolved_at": "now",
        }
    
        # Make request
        try:
            response = requests.put(
                api_url,
                json=data,
                headers=auth_manager.get_headers(),
                timeout=config.timeout,
            )
            response.raise_for_status()
    
            result = response.json().get("result", {})
    
            return IncidentResponse(
                success=True,
                message="Incident resolved successfully",
                incident_id=result.get("sys_id"),
                incident_number=result.get("number"),
            )
    
        except requests.RequestException as e:
            logger.error(f"Failed to resolve incident: {e}")
            return IncidentResponse(
                success=False,
                message=f"Failed to resolve incident: {str(e)}",
            )
  • Pydantic model defining input parameters for the resolve_incident tool.
    class ResolveIncidentParams(BaseModel):
        """Parameters for resolving an incident."""
    
        incident_id: str = Field(..., description="Incident ID or sys_id")
        resolution_code: str = Field(..., description="Resolution code for the incident")
        resolution_notes: str = Field(..., description="Resolution notes for the incident")
  • MCP tool registration in get_tool_definitions, mapping name to implementation, params schema, return type, description, and serialization.
    "resolve_incident": (
        resolve_incident_tool,
        ResolveIncidentParams,
        str,
        "Resolve an incident in ServiceNow",
        "str",
    ),
  • Re-export of resolve_incident function from incident_tools for use across the tools package.
    from servicenow_mcp.tools.incident_tools import (
        add_comment,
        create_incident,
        list_incidents,
        resolve_incident,
        update_incident,
    )
  • Import alias used in tool registration.
        resolve_incident as resolve_incident_tool,
    )
Behavior2/5

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

No annotations are provided, so the description carries the full burden. 'Resolve' implies a mutation that changes an incident's state, but the description doesn't disclose behavioral traits such as required permissions, whether this action is reversible, what happens to related records, or typical response formats. This is inadequate for a mutation tool with zero annotation coverage.

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 waste—it directly states the tool's purpose without unnecessary words. It's appropriately sized and front-loaded, 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?

Given the complexity of a mutation tool with no annotations and no output schema, the description is insufficient. It lacks critical context such as behavioral details (e.g., side effects, error conditions), usage guidelines relative to siblings, and any information about return values or success indicators, leaving significant gaps for an AI agent.

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 (incident_id, resolution_code, resolution_notes) with clear descriptions. The description adds no additional meaning beyond what the schema provides, such as explaining what resolution codes are valid or how notes are used, resulting in the baseline score of 3.

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 clearly states the action ('Resolve') and resource ('an incident in ServiceNow'), making the purpose immediately understandable. However, it doesn't differentiate from sibling tools like 'update_incident' or 'create_incident' that also operate on incidents, missing specific distinction about what 'resolve' entails versus general updates.

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?

No guidance is provided on when to use this tool versus alternatives. With siblings like 'update_incident' and 'create_incident' available, the description doesn't clarify that this is specifically for closing incidents with resolution details, nor does it mention prerequisites (e.g., incident must be in an open state) or exclusions.

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