Tune AD and alerting tool descriptions

[ohltyler]

Description

This PR enhances the default descriptions of the AD and alerting tools in several ways:

• more specific on the expected input types and returned output types (e.g., timestamps in epoch milliseconds format) to help guide the LLM to have valid suggestions when the tool generates the relevant search query / API calls.
• adds options for params that are not clearly defined or interfaced (e.g., monitor types, alert state, alert severity level)
• minor wording changes

It also fixes the parsing of the SearchMonitorsTool to parse monitor_type instead of type. type always is monitor, but monitor_type provides more detail, such as if the monitor is a query-level, bucket-level, or document-level monitor, which is more useful / user-expected

Variety of questions were tested on a test cluster with a provisioned LLM, and this PR is a direct result of where gaps were seen to help increase the effectiveness and accuracy of the tool itself.

Check List

• New functionality includes testing.
  • All tests pass
• New functionality has been documented.
  • New functionality has javadoc added
• Commits are signed per the DCO using --signoff

By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.
For more information on following Developer Certificate of Origin and signing off your commits, please check here.

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Comparison is base (722bfd2) 81.73% compared to head (0b51d31) 81.73%.

Additional details and impacted files

@@            Coverage Diff            @@
##               main     #154   +/-   ##
=========================================
  Coverage     81.73%   81.73%           
  Complexity      196      196           
=========================================
  Files            13       13           
  Lines          1002     1002           
  Branches        132      132           
=========================================
  Hits            819      819           
  Misses          133      133           
  Partials         50       50           

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[ohltyler]

All tests are passing besides known issue with neural sparse search tool:

30 tests completed, 2 failed
Tests with failures:
 - org.opensearch.integTest.NeuralSparseSearchToolIT.testNeuralSparseSearchToolInFlowAgent_withIllegalSourceField_thenGetEmptySource
 - org.opensearch.integTest.NeuralSparseSearchToolIT.testNeuralSparseSearchToolInFlowAgent_withIllegalEmbeddingField_thenThrowException