Update maxToolCalls and minToolCalls in eval.yaml

[janisz]

Description

Adjust tool calls to match gpt micro results

Validation

CI

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 78.49%. Comparing base (18d456a) to head (0c1322a).
✅ All tests successful. No failed tests found.

Additional details and impacted files

@@           Coverage Diff           @@
##             main      #65   +/-   ##
=======================================
  Coverage   78.49%   78.49%           
=======================================
  Files          28       28           
  Lines        1223     1223           
=======================================
  Hits          960      960           
  Misses        223      223           
  Partials       40       40           

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

[github-actions]

E2E Test Results

Commit: 0c1322a
Workflow Run: View Details

=== Evaluation Summary ===

  ✓ list-clusters (assertions: 3/3)
  ✓ cve-detected-workloads (assertions: 3/3)
  ✓ cve-detected-clusters (assertions: 3/3)
  ✓ cve-nonexistent (assertions: 3/3)
  ✓ cve-cluster-does-exist (assertions: 3/3)
  ~ cve-cluster-does-not-exist (assertions: 2/3)
      - ToolsUsed: Required tool not called: server=stackrox-mcp, tool=, pattern=list_clusters
  ✓ cve-clusters-general (assertions: 3/3)
  ✓ cve-cluster-list (assertions: 3/3)
  ✓ cve-log4shell (assertions: 3/3)
  ✓ cve-multiple (assertions: 3/3)
  ✓ rhsa-not-supported (assertions: 2/2)

Tasks:      11/11 passed (100.00%)
Assertions: 31/32 passed (96.88%)
Agent used tokens:
  Input:  30644 tokens
  Output: 21689 tokens
Judge used tokens:
  Input:  9713 tokens
  Output: 13173 tokens