Skip to main content
Glama

delete_agent_memory

Destructive

Removes one persistent agent memory for a specified agent, user, and scope; protected platform control entries cannot be deleted with this action.

Instructions

Delete one persistent agent memory. Platform control entries are protected and cannot be removed here.

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>",
      "memory_key": "<memory_key>",
      "user_key": "<user_key>"
    },
    "name": "delete_agent_memory"
  }
}

Input Schema

NameRequiredDescriptionDefault
scopeNoMemory scope; defaults to agent_user. The same key can exist in different scopes.
agent_idYesAgent UUID
user_keyYesIdentity of the end user who owns the memory
memory_keyYesMemory key to remove

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv2.2.4
    • changedInput schema / properties / agent_id / description
      Previous value: -"UUID do agente"New value: +"Agent UUID"
    • changedInput schema / properties / memory_key / description
      Previous value: -"Chave da memória a ser removida"New value: +"Memory key to remove"
    • changedInput schema / properties / scope / description
      Previous value: -"Escopo da memória (default agent_user). A mesma chave pode existir em escopos diferentes."New value: +"Memory scope; defaults to agent_user. The same key can exist in different scopes."
    • changedInput schema / properties / user_key / description
      Previous value: -"Identificador do usuário final dono da memória"New value: +"Identity of the end user who owns the memory"
  2. Changed1 schema field changedv2.2.2
    • addedInput schema / properties / scope
      Added value: +{
      +  "description": "Escopo da memória (default agent_user). A mesma chave pode existir em escopos diferentes.",
      +  "enum": [
      +    "agent_user",
      +    "tenant_user",
      +    "tenant_global"
      +  ],
      +  "type": "string"
      +}
  3. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, idempotentHint=false, and readOnlyHint=false, so the safety profile is covered. The description adds a genuine behavioral constraint (protected control entries are rejected), but says nothing about permanence, error behavior when the key is absent, or cross-scope effects — notable because the schema warns the same key can exist in multiple scopes.

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?

Two short sentences, front-loaded with the action and followed by the one real caveat; nothing is padded. It is efficient, though extremely terse relative to the semantics of a destructive operation.

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?

No output schema exists, so return values need not be explained, and annotations carry the destructive/idempotency profile. What remains thin is scope-dependent deletion behavior, but the schema documents that directly, leaving the definition adequate for a 4-parameter delete.

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%, so all four parameters including the scope enum are documented in the schema; baseline 3 applies. The description adds no meaning beyond it — notably it never mentions that scope selection determines which copy of a duplicated key is deleted.

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 ('Delete one persistent agent memory') and scopes it to a single item, which separates it from bulk/session tools. It does not explicitly contrast with the obvious sibling list_agent_memory or with delete_agent, so differentiation is only partial.

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?

The 'protected platform control entries cannot be removed here' clause implies a boundary on when this tool applies, but there is no explicit when-to-use vs. alternative guidance. An agent must infer that listing/reading memory is a separate tool and that protected entries need another path.

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