Skip to main content
Glama

linear_createIssue

Create a new issue in Linear project management with title, description, team assignment, priority, due dates, and labels to track and organize work items.

Instructions

Create a new issue in Linear

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
titleYesTitle of the issue
descriptionNoDescription of the issue (Markdown supported)
teamIdYesID of the team the issue belongs to
assigneeIdNoID of the user to assign the issue to
priorityNoPriority of the issue (0 = No priority, 1 = Urgent, 2 = High, 3 = Normal, 4 = Low)
projectIdNoID of the project the issue belongs to
cycleIdNoID of the cycle to add the issue to
estimateNoThe estimated complexity/points for the issue
dueDateNoThe date at which the issue is due (YYYY-MM-DD format)
labelIdsNoIDs of the labels to attach to the issue
parentIdNoID of the parent issue (to create as a sub-task)
subscriberIdsNoIDs of the users to subscribe to the issue
stateIdNoID of the workflow state for the issue
templateIdNoID of a template to use for creating the issue
sortOrderNoThe position of the issue in relation to other issues

Implementation Reference

  • The core handler function for the linear_createIssue tool. It validates the input arguments using isCreateIssueArgs type guard and delegates the creation to LinearService.createIssue.
    export function handleCreateIssue(linearService: LinearService) {
      return async (args: unknown) => {
        try {
          if (!isCreateIssueArgs(args)) {
            throw new Error('Invalid arguments for createIssue');
          }
    
          return await linearService.createIssue(args);
        } catch (error) {
          logError('Error creating issue', error);
          throw error;
        }
      };
    }
  • The tool definition (schema) for linear_createIssue, specifying input parameters (e.g., title, teamId required) and output structure.
    export const createIssueToolDefinition: MCPToolDefinition = {
      name: 'linear_createIssue',
      description: 'Create a new issue in Linear',
      input_schema: {
        type: 'object',
        properties: {
          title: {
            type: 'string',
            description: 'Title of the issue',
          },
          description: {
            type: 'string',
            description: 'Description of the issue (Markdown supported)',
          },
          teamId: {
            type: 'string',
            description: 'ID of the team the issue belongs to',
          },
          assigneeId: {
            type: 'string',
            description: 'ID of the user to assign the issue to',
          },
          priority: {
            type: 'number',
            description:
              'Priority of the issue (0 = No priority, 1 = Urgent, 2 = High, 3 = Normal, 4 = Low)',
          },
          projectId: {
            type: 'string',
            description: 'ID of the project the issue belongs to',
          },
          cycleId: {
            type: 'string',
            description: 'ID of the cycle to add the issue to',
          },
          estimate: {
            type: 'number',
            description: 'The estimated complexity/points for the issue',
          },
          dueDate: {
            type: 'string',
            description: 'The date at which the issue is due (YYYY-MM-DD format)',
          },
          labelIds: {
            type: 'array',
            items: { type: 'string' },
            description: 'IDs of the labels to attach to the issue',
          },
          parentId: {
            type: 'string',
            description: 'ID of the parent issue (to create as a sub-task)',
          },
          subscriberIds: {
            type: 'array',
            items: { type: 'string' },
            description: 'IDs of the users to subscribe to the issue',
          },
          stateId: {
            type: 'string',
            description: 'ID of the workflow state for the issue',
          },
          templateId: {
            type: 'string',
            description: 'ID of a template to use for creating the issue',
          },
          sortOrder: {
            type: 'number',
            description: 'The position of the issue in relation to other issues',
          },
        },
        required: ['title', 'teamId'],
      },
      output_schema: {
        type: 'object',
        properties: {
          id: { type: 'string' },
          identifier: { type: 'string' },
          title: { type: 'string' },
          url: { type: 'string' },
        },
      },
    };
  • Registration of the linear_createIssue handler within the registerToolHandlers function, mapping the tool name to the wrapped handleCreateIssue function.
    linear_createIssue: handleCreateIssue(linearService),
  • Type guard function isCreateIssueArgs used by the handler to validate input arguments before calling the Linear service.
     * Type guard for linear_createIssue tool arguments
     */
    export function isCreateIssueArgs(args: unknown): args is {
      title: string;
      description?: string;
      teamId: string;
      assigneeId?: string;
      priority?: number;
      projectId?: string;
      cycleId?: string;
      estimate?: number;
      dueDate?: string;
      labelIds?: string[];
      parentId?: string;
      subscriberIds?: string[];
      stateId?: string;
      templateId?: string;
      sortOrder?: number;
    } {
      return (
        typeof args === 'object' &&
        args !== null &&
        'title' in args &&
        typeof (args as { title: string }).title === 'string' &&
        'teamId' in args &&
        typeof (args as { teamId: string }).teamId === 'string' &&
        (!('assigneeId' in args) || typeof (args as { assigneeId: string }).assigneeId === 'string') &&
        (!('priority' in args) || typeof (args as { priority: number }).priority === 'number') &&
        (!('projectId' in args) || typeof (args as { projectId: string }).projectId === 'string') &&
        (!('cycleId' in args) || typeof (args as { cycleId: string }).cycleId === 'string') &&
        (!('estimate' in args) || typeof (args as { estimate: number }).estimate === 'number') &&
        (!('dueDate' in args) || typeof (args as { dueDate: string }).dueDate === 'string') &&
        (!('labelIds' in args) || Array.isArray((args as { labelIds: string[] }).labelIds)) &&
        (!('parentId' in args) || typeof (args as { parentId: string }).parentId === 'string') &&
        (!('subscriberIds' in args) ||
          Array.isArray((args as { subscriberIds: string[] }).subscriberIds)) &&
        (!('stateId' in args) || typeof (args as { stateId: string }).stateId === 'string') &&
        (!('templateId' in args) || typeof (args as { templateId: string }).templateId === 'string') &&
        (!('sortOrder' in args) || typeof (args as { sortOrder: number }).sortOrder === 'number')
      );
    }
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. It states the tool creates an issue but doesn't mention authentication requirements, rate limits, whether the operation is idempotent, what happens on failure, or what the return value looks like (no output schema). For a mutation tool with 15 parameters, 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 that states the core purpose without unnecessary words. It's appropriately sized for a creation tool and front-loads the essential information. Every word earns its place.

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 complex mutation tool with 15 parameters, no annotations, and no output schema, the description is inadequate. It doesn't explain what happens after creation, error conditions, authentication needs, or provide any context about Linear's issue system. The agent would struggle to use this tool effectively without external knowledge.

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 15 parameters thoroughly with descriptions and formats. The description adds no additional parameter information beyond what's in the schema. According to the rules, when schema coverage is high (>80%), the baseline is 3 even with no param info in the description.

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 ('Create a new issue') and resource ('in Linear'), making the purpose immediately understandable. It distinguishes from siblings like 'linear_duplicateIssue' or 'linear_updateIssue' by specifying creation rather than modification or duplication. However, it doesn't explicitly differentiate from all siblings (e.g., 'linear_createProject' follows a similar pattern).

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 (like needing teamId), when to choose this over 'linear_duplicateIssue' or 'linear_updateIssue', or any contextual constraints. The agent must infer usage solely from the tool name and parameters.

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/tacticlaunch/mcp-linear'

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