Skip to main content
Glama

jira_create_issue

Create a new Jira issue (bug, task, story, epic, or subtask) in a project. Returns the new issue key and URL for tracking.

Instructions

Create a new Jira issue (bug, task, story, epic, subtask, etc.) in a project. Use jira_get_issue_types first if unsure which issue types are available. For subtasks, provide the parentKey. For custom fields, pass customFields keyed by field id or a unique name from jira_get_create_meta (not jira_get_fields). Returns the new issue key and URL.

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": {
      "projectKey": "<projectKey>",
      "issueType": "<issueType>",
      "summary": "<summary>"
    },
    "name": "jira_create_issue"
  }
}

Input Schema

NameRequiredDescriptionDefault
labelsNoLabels to add
dueDateNoDue date in YYYY-MM-DD format
summaryYesIssue title/summary - a brief description of the issue
assigneeNoUsername to assign the issue to
priorityNoPriority name (e.g., High, Medium, Low)
issueTypeYesIssue type name (e.g., Bug, Task, Story, Epic, Sub-task). Use jira_get_issue_types to see available types
parentKeyNoParent issue key for subtasks
componentsNoComponent names
projectKeyYesProject key (e.g., KP). Use jira_get_projects to list available projects
descriptionNoIssue description
fixVersionsNoFix version names
customFieldsNoCustom fields keyed by field id (e.g. customfield_10006) or a unique name from that issue type's meta. Values are raw Jira REST payloads, not display names. Call jira_get_create_meta for schema/allowedValues and unique names. Examples: number 5, string "text", select {"value":"Yes"}, Server user {"name":"username"}, multi-select [{"value":"A"}], null to clear. Do not call jira_get_fields before create.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.1

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations present, the description carries the full load and does disclose the key outcome ('Returns the new issue key and URL') and the subtask/parent relationship, which an agent cannot infer from the schema. It does not mention permissions, side effects on notifications, or failure behavior, so it stops short of full behavioral coverage for a mutation tool.

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?

Four short sentences, front-loaded with the core action, then prerequisites, then the return value. There is no filler and each sentence carries a distinct operational instruction.

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

Completeness4/5

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

For a 12-parameter mutation tool with a nested customFields object, no annotations, and no output schema, the description covers the ambiguous parts: issue-type discovery, subtask parent linkage, custom field sourcing, and the return value. It leaves out permission requirements and what happens when referenced labels/components/versions do not exist, which are the remaining gaps.

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% and the customFields property is already documented in detail (raw REST payloads, examples, null to clear), so the description largely repeats rather than extends the schema. It does add the link between parentKey and subtasks, but most of its content duplicates structured fields, fitting the baseline for high coverage.

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

Purpose5/5

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

The description opens with a specific verb and resource ('Create a new Jira issue') and enumerates the issue types it covers (bug, task, story, epic, subtask), which cleanly separates it from the other jira_create_* siblings such as jira_create_link, jira_create_sprint, and jira_create_version.

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

Usage Guidelines5/5

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

It gives explicit prerequisites and routing: check jira_get_issue_types first if the issue type is unknown, supply parentKey for subtasks, and pull custom field ids/unique names from jira_get_create_meta rather than jira_get_fields. That is a concrete when-to-use and an explicit when-not-to-use of a sibling.

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