Skip to main content
Glama

list_agent_memory

Read-onlyIdempotent

List persistent memory entries for an AI agent and filter by category, scope, user, or page through results to review stored facts, preferences, instructions, and context.

Instructions

List persistent memory entries for an agent

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": {
      "agent_id": "<agent_id>"
    },
    "name": "list_agent_memory"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMemories per page; defaults to 50
scopeNoMemory scope; agent_user is person-scoped. The same memory key can exist in different scopes.
beforeNoPagination cursor: updated_at from the previous page's last entry
includeNoInclude the consumer's original statement that produced the memory. Contains personal data. Requires admin/owner; ignored for other roles.
agent_idYesAgent UUID
categoryNoFilter by memory category
user_keyNoFilter by user_key identifying the end user

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv2.2.4
    • changedInput schema / properties / agent_id / description
      Previous value: -"UUID do agente"New value: +"Agent UUID"
    • changedInput schema / properties / before / description
      Previous value: -"Paginação: `updated_at` do último item da página anterior"New value: +"Pagination cursor: updated_at from the previous page's last entry"
    • changedInput schema / properties / category / description
      Previous value: -"Filtrar por categoria de memória"New value: +"Filter by memory category"
    • changedInput schema / properties / include / description
      Previous value: -"provenance = frase original do consumidor que gerou a memória (PII). Só key admin/owner; para outros papéis é ignorado em silêncio (mesma regra do REST)."New value: +"Include the consumer's original statement that produced the memory. Contains personal data. Requires admin/owner; ignored for other roles."
    • changedInput schema / properties / limit / description
      Previous value: -"Máximo de memórias por página (default 50)"New value: +"Memories per page; defaults to 50"
    • changedInput schema / properties / scope / description
      Previous value: -"Filtrar por escopo (agent_user = por pessoa; a mesma chave pode existir em escopos diferentes)"New value: +"Memory scope; agent_user is person-scoped. The same memory key can exist in different scopes."
    • changedInput schema / properties / user_key / description
      Previous value: -"Filtrar por user_key específico (identifica o usuário final)"New value: +"Filter by user_key identifying the end user"
  2. Changed2 schema fields changedv2.2.3
    • addedInput schema / properties / include
      Added value: +{
      +  "description": "provenance = frase original do consumidor que gerou a memória (PII). Só key admin/owner; para outros papéis é ignorado em silêncio (mesma regra do REST).",
      +  "enum": [
      +    "provenance"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / scope
      Added value: +{
      +  "description": "Filtrar por escopo (agent_user = por pessoa; a mesma chave pode existir em escopos diferentes)",
      +  "enum": [
      +    "agent_user",
      +    "tenant_user",
      +    "tenant_global"
      +  ],
      +  "type": "string"
      +}
  3. Changed3 schema fields changedv2.2.2
    • addedInput schema / properties / before
      Added value: +{
      +  "description": "Paginação: `updated_at` do último item da página anterior",
      +  "type": "string"
      +}
    • changedInput schema / properties / category / enum
      Previous value: -[
      -  "fact",
      -  "preference",
      -  "instruction",
      -  "context",
      -  "schedule_report"
      -]New value: +[
      +  "fact",
      +  "preference",
      +  "instruction",
      +  "context"
      +]
    • addedInput schema / properties / limit
      Added value: +{
      +  "description": "Máximo de memórias por página (default 50)",
      +  "maximum": 200,
      +  "minimum": 1,
      +  "type": "integer"
      +}
  4. First observedv0.1.0

TDQS

C2.9/5.0
Behavior2/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds nothing beyond that — no note on pagination behavior, page-size limits, or that the 'include=provenance' option can be silently ignored for non-admin roles, which is exactly the kind of context the description should surface.

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?

One short, front-loaded sentence with zero redundant wording. It is efficient but has no structure beyond a single clause, leaving no room for the operational hints this tool needs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With seven parameters, three enums, cursor-based pagination, and a privacy-sensitive provenance option, this is a non-trivial query tool with no output schema. A single sentence leaves pagination iteration, scope selection, and the privacy caveat entirely to the schema, which is too thin for this complexity.

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 description coverage is 100%, with all seven parameters documented including enum meanings and the cursor semantics for 'before', so the schema carries the load and the baseline of 3 applies. The description contributes no additional meaning about any parameter.

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?

The description gives a specific verb ('List') and resource ('persistent memory entries') scoped to an agent, so the agent knows exactly what is returned. It does not distinguish itself from siblings such as delete_agent_memory or clarify list-vs-get semantics, so it stops short of a 5.

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

Usage Guidelines2/5

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

There is no when-to-use guidance: nothing says when to list memories versus retrieving a single memory or inspecting history, and no prerequisites are stated. Usage is only inferable from the phrase 'for an agent'.

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

Deploy Server

Other Tools