feat: Add tool annotations for improved LLM tool understanding

[triepod-ai]

Summary

Adds MCP tool annotations (readOnlyHint, destructiveHint) to all 19 tools to help LLMs better understand tool behavior and make safer decisions about tool execution.

Changes

• Added readOnlyHint: true to read-only tools:
  • list_containers
  • fetch_container_logs
  • list_images
  • list_networks
  • list_volumes
• Added destructiveHint: true to tools that create/update/delete data:
  • create_container, run_container, recreate_container
  • start_container, stop_container, remove_container
  • pull_image, push_image, build_image, remove_image
  • create_network, remove_network
  • create_volume, remove_volume
• Added title annotations for human-readable display on all tools
• Bump MCP SDK dependency from >=1.1.0 to >=1.8.0 for annotation support

Why This Matters

• Annotations provide semantic metadata that helps LLMs understand tool behavior
• LLMs can make better decisions about when to use tools and in what order
• Enables safer tool execution by distinguishing read-only from destructive operations
• Read-only tools can be used for information gathering without side effects
• Destructive operations can be batched or confirmed before execution

Testing

• Server builds successfully with uv sync
• All 19 tools have annotations verified programmatically
• Annotation values match actual tool behavior

Before/After

Before:

types.Tool(
    name="list_containers",
    description="List all Docker containers",
    inputSchema=ListContainersInput.model_json_schema(),
)

After:

types.Tool(
    name="list_containers",
    description="List all Docker containers",
    inputSchema=ListContainersInput.model_json_schema(),
    annotations=ToolAnnotations(
        title="List Containers",
        readOnlyHint=True,
    ),
)

🤖 Generated with Claude Code