feat: added get_pages tool as a replacement for get_page

[xscratt]

Description of changes

Added get_pages that supports returning multiple pages at once as a replacement of get_page tool.

Tool response has the following format:

{
  "content": [{
    "type": "text",
    "content": "[Document 1, Page 1]"
  }, {
    "type": "text",
    "content": "<aggregated text content of page 1>"
  }, {
    "type": "image",
    "imageType": "image/png",
    "data": "<base64-encoded page image of page 1>"
  }, {
    "type": "text",
    "content": "[Document 1, Page 2]"
  }, {
    "type": "text",
    "content": "<aggregated text content of page 2>"
  }, {
    "type": "image",
    "imageType": "image/png",
    "data": "<base64-encoded page image of page 2>"
  }]
}

BREAKING CHANGE: get_page tool is removed.

Checklist

• Title of the pull request follows Conventional Commits specification

By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.

[navalnica]

can we add a safeguard that limits number of pages requested in a single tool call? like max 10 images?