Skip to main content
Glama
furui

furui

Forget

forget

Permanently delete a single memory by its ID, including pinned entries, to remove specific stored data from an AI agent’s long-term memory.

Instructions

Permanently delete one memory by id (works on pinned memories too).

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

Input Schema

NameRequiredDescriptionDefault
idYesThe memory id returned by remember / recall.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does well: 'permanently' makes irreversibility explicit, and '(works on pinned memories too)' warns that pinning provides no protection against deletion. It omits error behavior for unknown ids and any authorization expectations, which keeps it from 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?

A single sentence with the destructive verb and the scope front-loaded, plus a parenthetical caveat that genuinely earns its place. No filler or redundant restatement of the name.

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 simple one-parameter destructive tool with an output schema and no annotations, the description covers the two things an agent most needs: irreversibility and the pinned-memory exception. Only failure-mode behavior is unaddressed.

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?

There is only one parameter and schema coverage is 100%, with the schema already noting the id comes from remember/recall. The description's 'by id' adds nothing beyond that, so the baseline of 3 applies.

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 pairs a precise verb ('permanently delete') with a precise resource ('one memory by id'), so the agent knows exactly what effect to expect. It stops short of explicitly differentiating itself from the sibling 'prune', leaving the single-vs-bulk distinction to inference.

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?

Usage is implied by the 'one memory by id' scoping, which nudges an agent toward this tool for targeted deletions, and the pinned note clarifies an important edge case. However, it never states when to prefer it over 'prune' or what happens if the id is stale, so the agent must infer the alternative-selection rule.

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