Skip to main content
Glama

Store a memory

memory_add

Store durable facts, decisions, or session notes as long-term memory in the active provider. Pass a project bank for scoped work; Hindsight ingests asynchronously by default.

Instructions

Store durable facts, decisions or session notes in the active provider. Pass bank from memory_project_scope for project work. Hindsight ingests async by default.

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": "memory_add"
  }
}

Input Schema

NameRequiredDescriptionDefault
bankNoHindsight bank or mem0 user_id / Cognee dataset scope (default: openmem-mcp)
asyncNoHindsight only: true (default) returns after enqueueing ingest; false waits for extraction (may hit MCP client timeouts).
contentYesPlain text to store as a durable memory
metadataNoOptional provider-specific metadata object

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.8.0
    • changedInput schema / properties / async / description
      Previous value: -"Hindsight only: queue background ingest (default true). Set false to wait for extraction (slow; may hit MCP timeouts)."New value: +"Hindsight only: true (default) returns after enqueueing ingest; false waits for extraction (may hit MCP client timeouts)."
    • changedInput schema / properties / bank / description
      Previous value: -"Hindsight bank or mem0 user_id scope (default: openmem-mcp)"New value: +"Hindsight bank or mem0 user_id / Cognee dataset scope (default: openmem-mcp)"
    • changedInput schema / properties / content / description
      Previous value: -"Text to remember"New value: +"Plain text to store as a durable memory"
    • changedInput schema / properties / metadata / description
      Previous value: -"Optional provider-specific metadata"New value: +"Optional provider-specific metadata object"
  2. First observedv0.6.3

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, idempotentHint=false and openWorldHint=true, so the base load is covered; the description then adds the important trait that Hindsight ingestion is async by default, which tells the agent why a memory may not be immediately retrievable. It does not say whether repeated identical adds create duplicates (relevant given idempotentHint=false) or what the provider fallback means for failure behavior.

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 short sentences, zero filler, and the core action is front-loaded before the conditional bank rule and the async caveat. Every clause carries information the agent can act on.

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?

There is no output schema, yet the description never says what a successful call returns (a memory id? per-provider confirmation?), which an agent would want in order to reference or later forget the record. Provider variation across Hindsight, mem0 and Cognee is named but not resolved, leaving meaningful ambiguity for a 4-parameter write tool.

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, but the description adds real meaning the schema lacks: that 'bank' should be sourced from memory_project_scope for project work, resolving provider ambiguity for that parameter. The async parameter's semantics are left entirely to the schema, which already explains the timeout trade-off.

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?

States a specific verb and resource — 'store durable facts, decisions or session notes' — and adds the concept of the 'active provider', which lets an agent tell it apart from retrieval siblings like memory_recall or memory_search. It never explicitly contrasts with memory_import or memory_capture_initiative, so the boundary against adjacent write tools stays implicit.

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?

'Pass bank from memory_project_scope for project work' is a concrete, actionable routing rule tied to a named sibling, which is genuinely useful. However, there is no guidance on when to use this instead of memory_import, memory_capture_initiative, or memory_consolidate, and no stated preconditions or exclusions beyond the bank hint.

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