Skip to main content
Glama

Save memory

store_memory

Use this after each user message that contains anything worth knowing later, even if the user does not say 'remember this'. Default to saving: a missed memory costs far more than a redundant one, so when in doubt, save. Each of these is a trigger on its own: the user makes a decision, states a preference, gives a fact about a person, project, company, or tool, sets a plan or commitment, makes a correction, or reports progress or an outcome. Save one concise, self-contained memory per call, written so it makes sense on its own later, with the exact wording, numbers, dates, names, and identifiers the user gave; several facts in one message mean several calls. Record what the user actually said, not your inference. There is no update tool: to supersede outdated information, save the corrected fact and say what it replaces. Never save passwords, API keys, tokens or other credentials, payment card numbers, government ID numbers, or protected health information, and never save whole transcripts. Writes one memory to the user's OAuth-selected vault. If the user asks what was saved, answer truthfully from the tool result.

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": "store_memory"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagsNoOptional short category labels. These are preserved as provenance text until structured tags ship.
contentYesOne concise, self-contained fact, preference, decision, commitment, correction, or outcome. Preserve exact wording, numbers, and identifiers when precision matters.

Output Schema

NameRequiredDescriptionDefault
sourceYes
statusYes
acceptedYes
vaultRefYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / content / description
      Previous value: -"The concise fact, preference, decision, or outcome the user approved for storage."New value: +"One concise, self-contained fact, preference, decision, commitment, correction, or outcome. Preserve exact wording, numbers, and identifiers when precision matters."
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations declare the operation is a non-idempotent, non-destructive write, and the description adds substantial context beyond them: the lack of an update tool, the supersede-via-correction pattern, explicit prohibitions on credentials and PII, the one-fact-per-call rule, and the vault-targeting behavior. This is genuinely helpful behavioral disclosure.

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 the trigger list before the operational constraints, and every sentence carries meaningful instruction. It is long, but for a high-frequency default-save tool the length is largely justified, with only minor redundancy in restating the 'self-contained' idea.

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 presence of annotations, a fully documented schema, and an output schema, the description covers everything an agent needs: when to invoke, granularity, format expectations, prohibited content, and the correction workflow. Nothing material is missing.

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 baseline is 3, but the description adds real semantic guidance: one self-contained memory per call, verbatim wording and identifiers, and multiple facts requiring multiple calls. The tags parameter is left to the schema, which is fine since it is fully documented there.

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 action and resource: 'Save one concise, self-contained memory per call' and 'Writes one memory to the user's OAuth-selected vault.' This clearly distinguishes it from siblings like delete_memories, forget_all_memories, and search_memories, which all operate on existing memories rather than creating new ones.

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

Usage Guidelines5/5

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

Provides explicit trigger conditions ('the user makes a decision, states a preference, gives a fact...'), a clear default policy ('Default to saving'), and a bias toward over-saving ('when in doubt, save'). It also specifies the no-update workflow, telling the agent to save a corrected fact and state what it replaces instead of looking for an update tool.

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.

Resources