[Feature]: Add jira_get_issue_images tool for inline image rendering

[sooperset]

Is your feature request related to a problem? Please describe.

jira_download_attachments returns all attachments (including images) as EmbeddedResource with base64-encoded blobs. Most MCP clients treat these as opaque binary data, so LLMs cannot visually interpret the image content.

Reported in #681: #681 (comment)

Describe the solution you'd like

Add a jira_get_issue_images tool that returns image attachments as ImageContent (from mcp.types), matching the existing confluence_get_page_images pattern. This enables MCP clients to render images natively for LLM vision.

Implementation reference

• Confluence equivalent: confluence_get_page_images in servers/confluence.py
• Two-tier MIME detection (explicit image types + filename extension fallback)
• Filter image attachments only, return as ImageContent

Use Case

Users downloading Jira image attachments expect AI to visually analyze the content — screenshots, diagrams, design mockups, etc. Currently there is no way to achieve this.