Update binlog mcp name

[JanKrivanek]

No description provided.

[JanKrivanek]

/evaluate

[Copilot]

Pull request overview

Updates the dotnet-msbuild plugin’s binlog MCP package name reference to align the MCP server installation command and the corresponding documentation/agent guidance.

Changes:

• Renamed the binlog MCP package from AITools.BinlogMcp to Microsoft.AITools.BinlogMcp in the plugin MCP server command.
• Updated all affected skill and agent documentation to reference the new MCP package name.
• Updated the allowed external dependency comment to reflect the new package name.

Show a summary per file

File	Description
plugins/dotnet-msbuild/skills/incremental-build/SKILL.md	Updates referenced binlog MCP package name in incremental-build guidance.
plugins/dotnet-msbuild/skills/eval-performance/SKILL.md	Updates referenced binlog MCP package name in evaluation-performance guidance.
plugins/dotnet-msbuild/skills/build-perf-diagnostics/SKILL.md	Updates referenced binlog MCP package name in perf diagnostics workflow.
plugins/dotnet-msbuild/skills/build-parallelism/SKILL.md	Updates referenced binlog MCP package name in parallelism analysis workflow.
plugins/dotnet-msbuild/skills/binlog-failure-analysis/SKILL.md	Updates referenced binlog MCP package name in failure analysis overview.
plugins/dotnet-msbuild/plugin.json	Updates MCP server dotnet dnx package argument to Microsoft.AITools.BinlogMcp.
plugins/dotnet-msbuild/agents/build-perf.agent.md	Updates referenced binlog MCP package name in agent instructions.
eng/allowed-external-deps.txt	Updates the dotnet-msbuild binlog MCP allowlist comment to match the new package name.

Copilot's findings

Tip

Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

• Files reviewed: 8/8 changed files
• Comments generated: 0

[github-actions]

Skill Validation Results

Skill	Scenario	Quality	Skills Loaded	Overfit	Verdict
build-parallelism	Analyze build parallelism bottlenecks	4.0/5 → 4.0/5	✅ build-parallelism; tools: skill, glob, binlog-binlog_overview, binlog-binlog_expensive_projects, binlog-binlog_expensive_targets, binlog-binlog_projects, binlog-binlog_diagnose, binlog-binlog_project_target_times / ⚠️ NOT ACTIVATED	✅ 0.13	❌ [1]
incremental-build	Analyze incremental build issues	3.0/5 → 3.7/5 🟢	✅ incremental-build; tools: skill, bash / ⚠️ NOT ACTIVATED	✅ 0.14	❌ [2]
build-perf-diagnostics	Diagnose slow build for a small project	4.0/5 → 4.3/5 🟢	⚠️ NOT ACTIVATED	🟡 0.30	❌ [3]
eval-performance	Analyze MSBuild evaluation performance issues	5.0/5 → 5.0/5	✅ eval-performance; tools: skill	✅ 0.13	❌ [4]
binlog-failure-analysis	Diagnose build failures from binlog only (no source files)	4.0/5 → 4.3/5 🟢	✅ binlog-failure-analysis; tools: binlog-binlog_overview, binlog-binlog_errors, binlog-binlog_items, binlog-binlog_search_files, binlog-binlog_files, skill / ⚠️ NOT ACTIVATED	✅ 0.11	✅

[1] ⚠️ High run-to-run variance (CV=218%) — consider re-running with --runs 5
[2] ⚠️ High run-to-run variance (CV=371%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -23.2% due to: judgment, tokens (26591 → 72933), quality, time (18.6s → 31.3s), tool calls (4 → 6)
[3] ⚠️ High run-to-run variance (CV=529%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -8.8% due to: tokens (27481 → 211868), tool calls (5 → 14), time (25.2s → 70.9s)
[4] ⚠️ High run-to-run variance (CV=63%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -7.6% due to: tokens (41711 → 84999), quality

⏰ timeout — run(s) hit the (160s) scenario timeout limit; scoring may be impacted by aborting model execution before it could produce its full output (increase via timeout in eval.yaml)

Model: claude-opus-4.6 | Judge: claude-opus-4.6

🔍 Full Results - additional metrics and failure investigation steps

▶ Sessions Visualisation -- interactive replay of all evaluation sessions