Skip to main content
Glama

Erase ALL memory for a user permanently (GDPR erasure)

delete_all
DestructiveIdempotent

Permanently erases stored memory and history across all spaces or a specified agent/run, enabling account deletion and GDPR compliance. Irreversible and distinct from history-preserving forgetting.

Instructions

PERMANENTLY erase memory (history included). With no agent_id/run_id, erases ALL of the user's memory across every space (account deletion / GDPR); pass them to erase just one space. Irreversible — not the same as forget, which retains history for audit.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "delete_all"
  }
}

Input Schema

NameRequiredDescriptionDefault
run_idNo
user_idNodefault
agent_idNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.11.0

TDQS

A4.8/5.0
Behavior5/5

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

Beyond `destructiveHint=true`, it discloses irreversibility, inclusion of history, and the potentially account-wide blast radius when scope identifiers are omitted. The audit-history distinction for `forget` adds further behavioral context rather than merely repeating annotations.

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?

The warning and action are front-loaded, followed immediately by scoping rules and the key sibling distinction. Every sentence conveys operationally important information with no filler.

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 highly destructive tool with no required parameters, it covers the critical safety, scope, and selection context; the output schema removes the need to describe return values. Full completeness would require resolving the remaining identifier-scope ambiguity and making the default user target explicit.

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?

With 0% schema description coverage, the description usefully explains that `agent_id` and `run_id` control scope and implicitly identifies the targeted user through `user_id`. It does not clarify whether either scope identifier can be supplied independently or explicitly explain the default `user_id` target.

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—permanently erasing a user's memory, including history—and defines both scoped and all-spaces operation. It also clearly distinguishes the tool from the sibling `forget`.

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?

It explicitly identifies account deletion and GDPR erasure as use cases for the unscoped call, while scoped identifiers select one space. The contrast with `forget`, which retains history for audit, supplies meaningful alternative-selection guidance.

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