Skip to main content
Glama

Save to RAMen Memory

remember
Idempotent

Save a lasting fact about the user—preferences, people, health, or plans—to shared memory so other AI apps recall it in future chats.

Instructions

Save a lasting fact about the user (their people, home, health, work, tastes, life plans) or what they ask you to remember, so their other AI apps know it next time. One clear sentence in their words. Not the details of the work in this chat: a saved chat keeps those.

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

Input Schema

NameRequiredDescriptionDefault
mustNotrue only when the user asks that every AI always keep this in mind (an allergy, a medicine, a diet, a disability, where they live, a hard limit)
noteYesthe fact in the user's words, for example 'My dentist is Dr. Lindqvist.'
quoteNothe user's exact words in this chat that the note comes from
profileNotrue for how the user wants answers (length, tone, format, what to call them): goes on their profile card, which every app gets
inferredNotrue if the user did not say it and you are guessing: it waits for their OK

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already cover safety (readOnlyHint=false, destructiveHint=false, idempotentHint=true), so the bar is lower, but the description adds real context the annotations cannot: saved facts propagate to 'their other AI apps', which explains the consequence of writing here. It also imposes a format constraint ('One clear sentence in their words'), though it says nothing about correction or removal.

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?

Three sentences, all load-bearing: the first defines the content and the cross-app payoff, the second sets the format, the third draws the boundary against chat history. Nothing is repeated from the schema and the exclusion is front-loaded where it matters.

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?

With five parameters, full schema coverage, and no output schema, the description covers what to save, how to phrase it, and what not to save. The remaining gap is post-write behavior — whether the fact is immediately visible, how it can be corrected — which an agent might want given this is a persistent write.

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?

Schema coverage is 100%, and each of must/note/quote/profile/inferred already carries a detailed description, so the baseline of 3 applies. The description adds only a light gloss on 'note' ('One clear sentence in their words') and the notion of facts the user asked to remember; it does not explain how must/profile/inferred interact with what gets saved.

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 gives a specific verb and resource ('Save a lasting fact about the user') and enumerates the scope of facts (people, home, health, work, tastes, life plans). It also explicitly carves out what this tool is not — 'Not the details of the work in this chat: a saved chat keeps those' — which separates it from save_thread without naming it.

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 states clearly when to use (durable personal facts or anything the user asks to remember) and when not to (chat-specific work details, which belong to a saved chat). The only shortfall is that it gestures at 'a saved chat' rather than naming the sibling tool that handles that case, leaving a small inference step.

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