Skip to main content
Glama
Sign In

memory

by com.leapmemory
OverviewDiscussionsAdmin

Memory save

remember

Save a piece of information to the user's long-term memory. The content is sent to LeapMemory's servers and stored in the user's account, so it persists across conversations and can be recalled later. The user can view and delete stored memories in the LeapMemory app. Use for durable facts the user shares about themselves, their world, or their preferences. Write the fact as a plain third-person statement about the user (e.g. 'The user prefers X'), never from your own point of view: no 'I will', 'awaiting', or references to yourself.

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": {
      "content": "<content>"
    },
    "name": "remember"
  }
}

Input Schema

NameRequiredDescriptionDefault
contentYesThe information to remember, as a clear sentence.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Goes well beyond the annotations: it discloses that content is sent to external LeapMemory servers, stored in the user's account, persists across conversations, and is user-viewable/deletable. It doesn't mention authentication requirements, but the external-transmission and persistence behavior are the important disclosures.

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?

Front-loads what the tool does, then adds the write-format constraint. Mostly tight, though the LeapMemory app sentence could be trimmed; every sentence still carries useful information.

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?

A single-param, non-destructive write with no output schema. The description covers persistence, privacy, usage criteria, and formatting rules, so an agent has what it needs. Only the return behavior is unstated, which is minor for a one-parameter write.

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 the baseline is 3. The description adds meaning beyond the schema: the content must be a plain third-person statement about the user, with concrete forbidden patterns ('I will', 'awaiting', self-reference). That's the main failure mode this tool has, and the description covers it.

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?

Specific verb+resource: saves information to the user's long-term memory. It clearly distinguishes itself from siblings like recall (read) and add_rule (rules), and the LeapMemory persistence model is spelled out.

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?

Explicitly says to use it for durable facts about the user, their world, or preferences, which rules out transient info. It doesn't name recall or add_rule as an alternative, but the usage condition is clear.

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

All memory toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources