agent-memory-mcp

memory_maintenance

Destructive

Perform maintenance on memory storage: expire old entries, purge orphans, rebuild full-text search, check graph integrity, clean duplicates, and run vacuum. Defaults to dry-run for safe preview.

Instructions

Explicit bounded maintenance. Defaults to dry-run. expire/orphans soft-delete; FTS rebuild and vacuum affect the whole DB. Physical purge is CLI-only.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>"
    },
    "name": "memory_maintenance"
  }
}

Input Schema

Name	Required	Description	Default
`id`	No
`limit`	No
`action`	Yes
`dry_run`	No
`project`	No
`after_id`	No
`namespace`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.1Sep 9, 2026

TDQS

A3.7/5.0

Behavior4/5

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

The description goes beyond the destructiveHint annotation by clarifying that expire/orphans perform soft-delete and that physical purge is not available here. It also discloses the dry-run default, making the tool's safety profile transparent.

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?

The description is concise, with no filler. Key facts are front-loaded: bounded maintenance, dry-run default, soft-delete, whole-DB effects, and CLI-only physical purge. Each sentence adds value.

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

Completeness3/5

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

While the description covers the main maintenance actions and safety constraints, it omits details about other parameters, output behavior, or specific use cases for each action. Given the tool's complexity (7 params, 9 enum values), the description provides a good starting point but is not fully complete.

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

Parameters3/5

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

The description explains the meaning of some enum values (expire/orphans soft-delete, FTS rebuild/vacuum whole DB) and the dry_run default, but does not cover parameters like id, limit, project, after_id, or namespace. Schema coverage is 0%, so the description partially compensates but leaves many parameters unexplained.

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

Purpose4/5

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

The description clearly indicates a maintenance tool with specific actions (expire, orphans, FTS rebuild, vacuum, etc.) and notes it is bounded and defaults to dry-run. While 'explicit bounded maintenance' is somewhat abstract, the action list and scope statement make the purpose understandable.

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

Usage Guidelines3/5

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

It mentions that expire/orphans soft-delete and that FTS rebuild/vacuum affect the whole DB, and that physical purge is CLI-only, which gives some guidance on when to use this tool vs. alternatives. However, it does not explicitly state scenarios for choosing this over other memory operations or detail prerequisites.

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