Skip to main content
Glama

Remember

remember
Idempotent

Save data the agent will need to reuse later, across this conversation or across sessions. Use when you discover something worth carrying forward (a resolved ticker, a target address, a user preference, a research subject) so you don't have to look it up again. Stored as a key-value pair scoped by your identifier. Authenticated users get persistent memory; anonymous sessions retain memory for 24 hours. Pair with recall to retrieve later, forget to delete.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "key": "target_ticker",
      "value": "AAPL"
    },
    "name": "remember"
  }
}

Input Schema

NameRequiredDescriptionDefault
kNoAlias for key.
vNoAlias for value.
keyYesMemory key (e.g., "subject_property", "target_ticker", "user_preference"). Accepts name, k, label as aliases.
dataNoAlias for value.
nameNoAlias for key.
textNoAlias for value.
labelNoAlias for key.
valueYesValue to store (any text, findings, addresses, preferences, notes). Accepts content, text, data, v as aliases; a non-string value is stored as JSON.
contentNoAlias for value.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / value / description
      Previous value: -"Value to store (any text — findings, addresses, preferences, notes). Accepts content, text, data, v as aliases; a non-string value is stored as JSON."New value: +"Value to store (any text, findings, addresses, preferences, notes). Accepts content, text, data, v as aliases; a non-string value is stored as JSON."
  2. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare this as a non-read-only, non-destructive, idempotent write; the description adds what they cannot: the persistence model (authenticated users get durable memory, anonymous sessions expire after 24 hours) and the key-value storage shape scoped by caller identity. What it omits is the overwrite semantics for an existing key, though idempotentHint=true partially covers that.

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?

Three sentences, front-loaded with purpose then trigger then lifecycle pairing, with no filler. The authentication/expiry sentence is dense but each clause carries distinct information an agent needs before deciding to persist something.

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 simple two-required-parameter write with no output schema, the description covers purpose, trigger, retention behavior, and sibling pairing. Nothing essential to calling it correctly is missing; a note on whether re-saving a key overwrites would close the last gap.

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%, so key/value, the required set, and all alias fields are already documented in structured data, setting the baseline at 3. The description contributes only the framing that storage is a key-value pair scoped by the caller's identifier, which adds little about how the individual parameters behave.

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 first sentence states a specific verb and resource ('Save data the agent will need to reuse later') and adds the scope ('across this conversation or across sessions'). It is clearly distinct from the named siblings recall (retrieve) and forget (delete), so an agent can route correctly without opening a schema.

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 gives a concrete trigger — 'when you discover something worth carrying forward' — with illustrative examples (resolved ticker, target address, user preference, research subject) and explicitly points to recall and forget for the other halves of the lifecycle. It lacks an explicit when-not clause (e.g., don't persist secrets or transient state), which keeps it short of a 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.