Skip to main content
Glama

forget

Destructive

Permanently deletes one memory entry by UUID, restricted to the agent's own agent-scope memories. Use remember with the same key to correct an entry instead of deleting it.

Instructions

Permanently delete one memory entry by its UUID. Agents can only delete their own agent-scope memories; project and workspace memories are refused. To correct an entry, call remember with the same key instead of deleting it.

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": {
      "memory_id": "<memory_id>"
    },
    "name": "forget"
  }
}

Input Schema

NameRequiredDescriptionDefault
memory_idYesUUID of the memory to delete: the id field of a recall(full=true) result, not its key.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.6
    • changedInput schema / properties / memory_id / description
      Previous value: -"UUID of the memory to delete."New value: +"UUID of the memory to delete: the id field of a recall(full=true) result, not its key."
  2. First observedv0.1.1

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 readOnlyHint=false, so the safety profile is covered; the description adds real value by specifying permanence and the authorization rule that agents may only delete their own agent-scope memories, with project/workspace memories refused. It does not explain failure behavior for unknown UUIDs or the non-idempotent repeat-delete case flagged in annotations, so it stops short of a 5.

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, each carrying distinct information: the action, the permission boundary, and the corrective alternative. The action is front-loaded and nothing is redundant.

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 one-parameter destructive tool with full annotation coverage and no output schema, the definition covers action, scope, permissions, and the main misuse case. Minor gap: it does not say what happens if the UUID does not exist or points to a memory the caller cannot see.

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?

Only one parameter, and the schema already documents it at 100% coverage, including the crucial detail that it is the id field from recall(full=true) rather than the key. The description's 'by its UUID' reinforces but adds nothing beyond the schema, so the high-coverage baseline of 3 applies.

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, resource, and identifier ('Permanently delete one memory entry by its UUID'), which cleanly separates it from siblings like remember, recall, and get_memory. An agent knows exactly what it does and what it does not do.

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

Usage Guidelines4/5

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

Gives an explicit when-not ('To correct an entry, call remember with the same key instead of deleting it') and names the alternative tool. It also constrains the universe of deletable memories, though it stops short of saying when deletion is the right call versus archiving or leaving entries alone.

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