Skip to main content
Glama
raalarcon9705

raalarcon-jira-mcp-server

update_issue

Update any field of an existing Jira issue, including summary, description, priority, assignee, labels, or convert it to a subtask. Only specified fields are modified.

Instructions

Update fields of an existing Jira issue or convert to subtask. Only provided fields will be updated. Use get_issue first to see current values. Returns success confirmation.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
issueKeyYesIssue key (e.g., "PROJ-123") to update. This is the unique identifier for the issue.
summaryNoNew issue title/summary (max 255 characters). Replaces the existing summary.
descriptionNoNew issue description. Replaces the existing description. Supports plain text, Markdown, or ADF. Markdown will be automatically converted to ADF. For mentions, use format: @[accountId:displayName] (get accountId from get_users tool).
priorityNoNew priority: "Highest", "High", "Medium", "Low", "Lowest". Replaces current priority.
assigneeNoAccount ID of new assignee. Use get_users to find account IDs. Set to null to unassign.
parentNoIssue key of the parent issue (e.g., "PROJ-123"). Use to convert issue to subtask or change parent.
labelsNoComplete array of labels (replaces all existing labels). Use empty array to remove all labels.
componentsNoComplete array of components (replaces all existing components). Use empty array to remove all components.
fixVersionsNoComplete array of fix versions (replaces all existing versions). Use empty array to remove all versions.
customFieldsNoCustom field values as key-value pairs. Only specified fields will be updated.

Implementation Reference

  • src/index.ts:39-61 (registration)
    The MCP server registers the update_issue tool via createIssueTools() and routes handleIssueTool() when name starts with 'update_issue' (see line 74).
    private setupHandlers() {
      // List available tools
      this.server.setRequestHandler(ListToolsRequestSchema, async () => {
        const projectTools = createProjectTools(this.jiraClient);
        const issueTools = createIssueTools(this.jiraClient);
        const commentTools = createCommentTools(this.jiraClient);
        const transitionTools = createTransitionTools(this.jiraClient);
        const assignmentTools = createAssignmentTools(this.jiraClient);
        const sprintTools = createSprintTools(this.jiraClient);
        const wikiTools = createWikiTools();
    
        return {
          tools: [
            ...projectTools,
            ...issueTools,
            ...commentTools,
            ...transitionTools,
            ...assignmentTools,
            ...sprintTools,
            ...wikiTools,
          ],
        };
      });
  • src/index.ts:71-77 (registration)
    Routes 'update_issue' calls to handleIssueTool dispatch function.
    } else if (
      name.startsWith('create_issue') ||
      name.startsWith('get_issue') ||
      name.startsWith('update_issue') ||
      name.startsWith('delete_issue')
    ) {
      return await handleIssueTool(name, args || {}, this.jiraClient);
  • The handler case for 'update_issue': validates args via updateIssueSchema, calls jiraClient.updateIssue(), and returns success message.
    case 'update_issue': {
      const validatedArgs = await updateIssueSchema.validate(args);
      const _result = await jiraClient.updateIssue(validatedArgs);
    
      return {
        content: [
          {
            type: 'text',
            text: `Issue ${validatedArgs.issueKey} updated successfully`,
          },
        ],
      };
    }
  • Validation schema for update_issue input: issueKey (required), summary, description (with markdown-to-ADF transform), priority, assignee, parent, labels, components, fixVersions, customFields (all optional).
    export const updateIssueSchema = yup.object({
      issueKey: yup.string().required('Issue key is required'),
      summary: yup.string().optional().max(255, 'Summary too long'),
      description: yup.mixed()
        .optional()
        .transform(function (value) {
          // If it's a string and looks like markdown, convert to ADF
          if (typeof value === 'string' && isMarkdown(value)) {
            return markdownToADF(value);
          }
          return value;
        }),
      priority: yup.string().optional(),
      assignee: yup.string().optional(),
      parent: yup.string().optional(),
      labels: yup.array().of(yup.string()).optional(),
      components: yup.array().of(yup.string()).optional(),
      fixVersions: yup.array().of(yup.string()).optional(),
      customFields: yup.object().optional(),
    });
  • JiraClient.updateIssue() builds a fields object from validated input and calls jira.issues.editIssue() to perform the API update.
    // Update an issue
    async updateIssue(input: UpdateIssueInput) {
      try {
        const updateData: { fields: Record<string, unknown> } = {
          fields: {},
        };
    
        if (input.summary) {
          updateData.fields.summary = input.summary;
        }
    
        if (input.description) {
          updateData.fields.description = input.description;
        }
    
        if (input.priority) {
          updateData.fields.priority = { name: input.priority };
        }
    
        if (input.assignee) {
          updateData.fields.assignee = { accountId: input.assignee };
        }
    
        if (input.parent) {
          updateData.fields.parent = { key: input.parent };
        }
    
        if (input.labels) {
          updateData.fields.labels = input.labels;
        }
    
        if (input.components) {
          updateData.fields.components = input.components.map(name => ({ name }));
        }
    
        if (input.fixVersions) {
          updateData.fields.fixVersions = input.fixVersions.map(name => ({ name }));
        }
    
        if (input.customFields) {
          Object.assign(updateData.fields, input.customFields);
        }
    
        const response = await this.jira.issues.editIssue({
          issueIdOrKey: input.issueKey,
          fields: updateData.fields,
        });
        return response;
      } catch (error) {
        throw new Error(`Failed to update issue: ${error instanceof Error ? error.message : 'Unknown error'}`);
      }
    }
Behavior3/5

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

With no annotations provided, the description carries full burden. It states that only provided fields are updated and returns 'success confirmation', but lacks details on permissions, error states, atomicity, or the behavior when the issue key is invalid. The conversion to subtask is mentioned but not elaborated.

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 three sentences, each serving a distinct purpose: main action, update behavior, prerequisite, return value. No unnecessary words, and it is front-loaded with the core functionality.

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 (10 parameters, no output schema, no annotations), the description is too brief. It lacks details on return format, error handling, idempotency, and edge cases like partial updates. The 'success confirmation' is vague, and the conversion to subtask behavior could be expanded.

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 description adds minimal value beyond the schema. It reiterates that only provided fields are updated, but does not provide new semantic details for specific parameters. The baseline of 3 is appropriate.

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 clearly states the tool updates fields of an existing Jira issue, including conversion to subtask. It uses specific verbs ('update', 'convert') and identifies the resource ('existing Jira issue'). It distinguishes from sibling tools like create_issue, transition_issue, or assign_issue.

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

Usage Guidelines4/5

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

The description explicitly advises to use 'get_issue first to see current values', providing a clear prerequisite. It implies usage for field updates and subtask conversion, but does not explicitly exclude using it for transitions or assignments, which are handled by sibling tools.

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/raalarcon9705/jira-mcp'

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