Skip to main content
Glama
total-agent-memory

total-agent-memory

memory_export

Read-onlyIdempotent

Export all agent knowledge, sessions, relations, and action logs as JSON for backup or migration. Supports paged snapshots and optional project filtering to move data safely.

Instructions

Export all knowledge as JSON for backup or migration. Includes knowledge, sessions, relations and the agent action log. Pass limit to export one page of a snapshot: the end line then carries complete=false and a next_cursor to pass back as cursor until complete=true. Pages of one export share a snapshot id and can be imported only as a complete, contiguous sequence. Sessions, relations and the action log come with the first page only.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "memory_export"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoRecords per page; omit for one unpaged export. Default with a cursor: 1000.
cursorNoOpaque next_cursor from the previous page's end line
formatNoJSON includes sessions and relations; JSONL streams knowledge with a header and completeness footer.json
projectNoExport only this project (optional)
save_to_fileNoSave to <memory-dir>/backups/ (default true)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv15.0.0
    • addedInput schema / properties / cursor
      Added value: +{
      +  "description": "Opaque next_cursor from the previous page's end line",
      +  "type": "string"
      +}
    • addedInput schema / properties / format
      Added value: +{
      +  "default": "json",
      +  "description": "JSON includes sessions and relations; JSONL streams knowledge with a header and completeness footer.",
      +  "enum": [
      +    "json",
      +    "jsonl"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / limit
      Added value: +{
      +  "description": "Records per page; omit for one unpaged export. Default with a cursor: 1000.",
      +  "maximum": 5000,
      +  "minimum": 1,
      +  "type": "integer"
      +}
  2. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already indicate a read-only, idempotent, non-destructive operation. The description adds important behavior beyond that: pagination uses a shared snapshot id, pages must be imported as a complete contiguous sequence, and sessions/relations/action log appear only on the first page.

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 dense and front-loaded, with no obvious filler. It packs several operational constraints into a short space, though the paging and import rules are slightly compressed and could be easier to scan.

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?

Given the tool's complexity, annotations, and lack of output schema, the description covers the critical information an agent needs: export contents, paged export semantics, snapshot consistency, and import requirements. The remaining parameter details are fully covered by the schema.

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%, so parameter documentation is already strong. The description still adds useful semantics about how limit and cursor interact, how the end line carries complete=false and next_cursor, and how to continue until complete=true.

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 states a specific verb and resource: export all knowledge as JSON for backup or migration. It also names exactly what is included (knowledge, sessions, relations, agent action log), making the operation unambiguous.

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?

It clearly positions the tool for backup or migration and explains the paged export workflow. It does not explicitly name alternative tools, but the intended usage context is concrete and the paging/import constraints provide practical guidance.

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