Skip to main content
Glama
multiinstance-jira-mcp

multiinstance-jira-mcp

by jmeronon-dev

Delete issue

jira_delete_issue
Destructive

Permanently deletes a Jira issue after confirmation, requiring delete permission; use it to remove unwanted or duplicate issues from a specified instance.

Instructions

Permanently delete an issue. Requires delete permission. Ask the user for confirmation first.

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": {
      "issue": "<issue>"
    },
    "name": "jira_delete_issue"
  }
}

Input Schema

NameRequiredDescriptionDefault
issueYesIssue key ('ABC-123'), instance-prefixed key ('work:ABC-123') or full browse URL ('https://acme.atlassian.net/browse/ABC-123').
instanceNoJira instance name (see jira_list_instances). Optional: calls are routed automatically by 'name:KEY' prefixes, issue URLs, project-key mapping, the default instance, or when only one instance exists.
deleteSubtasksNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.3/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the destructive nature is structured data. The description still adds value by specifying that the deletion is permanent and requires delete permission. It omits important behavioral details: what happens to child issues, comments, and links, whether an attempt with subtasks fails unless deleteSubtasks is set, and whether the response returns anything.

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?

Three short sentences, front-loaded with the action and its permanence, then the permission prerequisite, then the confirmation rule. No wasted wording and no buried information.

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

Completeness3/5

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

For a destructive mutation with no output schema, the description covers safety (permanent, needs permission, confirm first), which is the core need. It leaves the deleteSubtasks behavior and the effect on related data unaddressed, so it is not fully complete for a 3-parameter destructive tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description never mentions any parameter, including deleteSubtasks, which has no description in the schema and is the parameter whose behavior is least obvious. The issue and instance parameters are already well documented in the schema at 67% coverage. As a result, the description compensates for none of the remaining coverage gap.

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?

"Permanently delete an issue" states a specific verb and resource with an explicit permanence qualifier. It does not name or contrast with siblings, though no other sibling in the catalog deletes, so the operation is effectively distinguishable by name alone.

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

Usage Guidelines3/5

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

It gives one concrete procedural rule ("Ask the user for confirmation first"), which is real when-to guidance for a destructive call. However, it offers no alternatives or exclusions, such as using jira_transition_issue to close rather than delete, or how to handle issues with subtasks.

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