Skip to main content
Glama

Erase a subject permanently (GDPR erasure)

delete
DestructiveIdempotent

Permanently erase every record of a subject—history and tombstones included—for GDPR or right-to-be-forgotten erasure. Use the subject key shown by list_memories.

Instructions

PERMANENTLY erase every record of a subject — including history and tombstones — for a user. Unlike forget (which retires but retains for audit), this is a hard delete for right-to-be-forgotten / GDPR erasure. The subject is the key shown by list_memories.

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": {
      "subject": "<subject>"
    },
    "name": "delete"
  }
}

Input Schema

NameRequiredDescriptionDefault
run_idNo
subjectYes
user_idNodefault
agent_idNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.11.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is known; the description still adds real value by specifying what is destroyed — history and tombstones, not just the current record. It stops short of explaining how the other identifiers (user_id, agent_id, run_id) widen or narrow the blast radius, or whether any confirmation step is required.

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 tight sentences with the irreversible nature front-loaded in capitals, followed by the sibling contrast and the key parameter hint. No filler and no repetition of annotation data.

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?

Return values need not be described because an output schema exists, and annotations carry the safety metadata. However, for a destructive multi-scope delete, the description leaves the interaction between `subject` and the tenant/agent/run identifiers unexplained, so an agent cannot fully predict what will be erased.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across four parameters, and the description explains only one of them: `subject`, identified as the key shown by `list_memories`. The scoping parameters `user_id`, `agent_id`, and `run_id` are undocumented in both the schema and the description, which matters greatly for a hard-delete tool.

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?

States a specific verb and resource ('PERMANENTLY erase every record of a subject'), plus the exact scope ('including history and tombstones'). It explicitly differentiates itself from the sibling `forget`, so an agent can choose between them without opening another schema.

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?

Names the selecting condition ('right-to-be-forgotten / GDPR erasure') and the alternative tool with its contrasting behavior ('forget ... retires but retains for audit'). That combination is effectively an explicit when-to-use / when-not-to-use rule.

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