Skip to main content
Glama

memory_list_compact

List memories in compact format with ID, preview, and tags to reduce context usage and browse efficiently without loading full content.

Instructions

List memories in compact format (id, preview, tags only) to reduce context usage.

Returns minimal fields: id, content preview (first 80 chars), tags, and created_at. This tool is useful for browsing memories without loading full content and metadata.

Args: query: Optional text search query metadata_filters: Optional metadata filters limit: Maximum number of results to return (default: unlimited) offset: Number of results to skip (default: 0) date_from: Optional date filter (ISO format or relative like "7d", "1m", "1y") date_to: Optional date filter (ISO format or relative like "7d", "1m", "1y") tags_any: Match memories with ANY of these tags (OR logic) tags_all: Match memories with ALL of these tags (AND logic) tags_none: Exclude memories with ANY of these tags (NOT logic)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryNo
metadata_filtersNo
limitNo
offsetNo
date_fromNo
date_toNo
tags_anyNo
tags_allNo
tags_noneNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • The implementation of the `memory_list_compact` tool, which retrieves a list of memories in a minimized format to save context tokens.
        help="Show sync status and backend information"
    )
    
    # Subcommand: info
    subparsers.add_parser(
        "info",
        help="Show storage backend information"
    )
    
    # Subcommand: migrate-images
    migrate_parser = subparsers.add_parser(
        "migrate-images",
        help="Migrate base64 images to R2 storage"
    )
    migrate_parser.add_argument(
        "--dry-run",
        action="store_true",
        help="Show what would be migrated without making changes"
    )
    
    args = parser.parse_args(argv)
    
    # Handle subcommands
    if args.command == "sync-pull":
        _handle_sync_pull()
    elif args.command == "sync-push":
        _handle_sync_push()
    elif args.command == "sync-status":
        _handle_sync_status()
    elif args.command == "info":
        _handle_info()
    elif args.command == "migrate-images":
        _handle_migrate_images(dry_run=args.dry_run)
    else:
        # Default: start server
        mcp.settings.host = args.host
        mcp.settings.port = args.port
    
        # Pre-warm database connection (triggers cloud sync if needed)
        # This prevents "connection failed" on first MCP connection
        try:
            import sys
            print("Initializing database...", file=sys.stderr)
            conn = connect()
            conn.close()
            print("Database ready.", file=sys.stderr)
        except Exception as e:
Behavior4/5

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

With no annotations provided, the description carries the full burden and successfully discloses key behavioral traits: the 80-character content truncation, the minimal field selection rationale (context reduction), and the read-only browsing nature. It could be improved by mentioning pagination defaults or empty result behavior, but the truncation detail is valuable.

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

Conciseness4/5

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

The description is well-structured with purpose front-loaded in the first sentence, followed by return value specifics, usage context, and a necessary Args section. Given the complete lack of schema documentation, the Args section is essential and efficiently formatted without redundancy.

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

Completeness4/5

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

For a tool with 9 optional parameters supporting complex filtering (date ranges, boolean tag logic, metadata), the description adequately covers the filtering semantics. Since an output schema exists (per context signals), the brief enumeration of returned fields is sufficient. It appropriately focuses on the tag logic nuances which are the most complex aspect.

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

Parameters5/5

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

The schema has 0% description coverage, but the description fully compensates by documenting all 9 parameters with precise semantics. It adds critical details absent from the schema: relative date formats ('7d', '1m', '1y'), boolean logic explanations for tag filters (OR/AND/NOT), and explicit default values (unlimited, 0).

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?

The description explicitly states the tool 'List memories in compact format' and distinguishes itself from sibling `memory_list` by emphasizing 'reduce context usage' and specifying the exact returned fields (id, preview, tags, created_at). The 80-character preview limit is also specified, clarifying the compact nature.

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

Usage Guidelines4/5

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

The description provides clear usage context ('useful for browsing memories without loading full content and metadata'), helping the agent understand when to use this over a full-fetch alternative. However, it does not explicitly name the sibling alternative (e.g., 'use memory_list instead for full content').

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/agentic-box/memora'

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