Skip to main content
Glama

adjust_memento_confidence

Manually adjust relationship confidence scores in MCP Memento to correct, verify, or override automatic decay based on user knowledge.

Instructions

Manually adjust confidence of a relationship.

Use for:

  • Correcting confidence scores when you know a memory is valid/invalid

  • Setting custom confidence based on verification

  • Overriding automatic decay for specific cases

Examples:

  • adjust_memento_confidence(relationship_id="rel-123", new_confidence=0.9, reason="Verified in production")

  • adjust_memento_confidence(relationship_id="rel-456", new_confidence=0.1, reason="Obsolete after library update")

Confidence ranges:

  • 0.9-1.0: High confidence (recently validated)

  • 0.7-0.89: Good confidence (regularly used)

  • 0.5-0.69: Moderate confidence (somewhat outdated)

  • 0.3-0.49: Low confidence (likely outdated)

  • 0.0-0.29: Very low confidence (probably obsolete)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
relationship_idYesID of the relationship to adjust
new_confidenceYesNew confidence value (0.0-1.0)
reasonNoReason for the adjustment

Implementation Reference

  • Handler function for the adjust_memento_confidence tool.
    async def handle_adjust_memento_confidence(
        memory_db: SQLiteMemoryDatabase, arguments: Dict[str, Any]
    ) -> CallToolResult:
        """Handle adjust_confidence tool call.
    
        Args:
            memory_db: Database instance for memory operations
            arguments: Tool arguments from MCP call containing:
                - relationship_id: ID of the relationship to adjust
                - new_confidence: New confidence value (0.0-1.0)
                - reason: Reason for the adjustment
    
        Returns:
            CallToolResult with confirmation or error message
        """
        relationship_id = arguments["relationship_id"]
        new_confidence = float(arguments["new_confidence"])
        reason = arguments.get("reason", "Manual adjustment")
    
        await memory_db.adjust_confidence(relationship_id, new_confidence, reason)
    
        return CallToolResult(
            content=[
                TextContent(
                    type="text",
                    text=f"Adjusted confidence for relationship {relationship_id} to {new_confidence:.2f}",
                )
            ]
        )
  • Registration of the adjust_memento_confidence tool in the MCP tool registry.
        handle_adjust_memento_confidence,
        handle_apply_memento_confidence_decay,
        handle_boost_memento_confidence,
        handle_get_low_confidence_mementos,
        handle_set_memento_decay_factor,
    )
    from .guide_tools import (
        handle_memento_onboarding,
    )
    from .memory_tools import (
        handle_delete_memento,
        handle_get_memento,
        handle_store_memento,
        handle_update_memento,
    )
    from .relationship_tools import (
        handle_create_memento_relationship,
        handle_get_related_mementos,
    )
    from .search_tools import (
        handle_contextual_memento_search,
        handle_recall_mementos,
        handle_search_mementos,
    )
    
    # Type alias for tool handlers
    ToolHandler = Callable[[Any, Dict[str, Any]], Awaitable[CallToolResult]]
    
    # Registry mapping tool names to handlers
    TOOL_HANDLERS: Dict[str, ToolHandler] = {
        "store_memento": handle_store_memento,
        "get_memento": handle_get_memento,
        "update_memento": handle_update_memento,
        "delete_memento": handle_delete_memento,
        "search_mementos": handle_search_mementos,
        "recall_mementos": handle_recall_mementos,
        "contextual_memento_search": handle_contextual_memento_search,
        "create_memento_relationship": handle_create_memento_relationship,
        "get_related_mementos": handle_get_related_mementos,
        "get_memento_statistics": handle_get_memento_statistics,
        "memento_onboarding": handle_memento_onboarding,
        "get_recent_memento_activity": handle_get_recent_memento_activity,
        "search_memento_relationships_by_context": handle_search_memento_relationships_by_context,
        # Confidence system tools
        "adjust_memento_confidence": handle_adjust_memento_confidence,
  • Tool definition/schema for adjust_memento_confidence.
    name="adjust_memento_confidence",
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full disclosure burden. Provides excellent behavioral context via confidence scale (0.0-1.0 ranges with semantic labels) and notes it 'Overriding automatic decay' indicating interference with background processes. Minor gap: doesn't explicitly state if adjustments are permanent or reversible.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Perfectly structured with clear sections: purpose statement, 'Use for' bullets, 'Examples' bullets, and 'Confidence ranges' reference. Front-loaded with the core action. Every line provides actionable guidance or domain context.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Comprehensive coverage for a confidence adjustment tool. Includes domain-specific knowledge (confidence scale interpretation), interaction patterns with automatic decay, and operational examples. No output schema exists, but none required given the action-oriented nature.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, establishing baseline 3. Description adds significant value: confidence ranges explain numeric semantics, and concrete examples demonstrate parameter usage patterns (reason='Verified in production').

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with specific verb 'adjust' targeting 'confidence of a relationship'. Implicitly distinguishes from sibling 'apply_memento_confidence_decay' (manual vs automatic) and 'boost_memento_confidence' (general adjustment vs specific boosting). The domain context (memento relationships) is clear.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit 'Use for:' section lists three specific scenarios including 'Overriding automatic decay' which clearly signals when to use this manual tool versus the automatic sibling. Concrete examples show valid/invalid correction cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/x-hannibal/mcp-memento'

If you have feedback or need assistance with the MCP directory API, please join our Discord server