Skip to main content
Glama

forget_memory

Remove a stored memory so it is no longer recalled; use when a memory is wrong, obsolete, or mistakenly saved. Removal is checkpointed, and the old version remains restorable in history.

Instructions

Remove a memory from the store so it is no longer recalled. CALL THIS: when a memory is wrong, obsolete or was saved by mistake and nothing replaces it. If a newer memory replaces it, call save_memory with supersedes instead, which keeps the link between the two. The removal is recorded as a checkpoint and the old version stays in history, so it can be restored; the response returns the forgotten memory so you can save it again if needed. Critical (priority 3) and core-guide memories need confirm=true.

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": {
      "slug": "<slug>"
    },
    "name": "forget_memory"
  }
}

Input Schema

NameRequiredDescriptionDefault
slugYesExact slug of the memory to forget.
reasonNoWhy it is being forgotten; recorded in the checkpoint message.
confirmNoRequired (true) to forget a priority-3 or core-guide memory.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.14.4

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so: it discloses that removal is a soft delete recorded as a checkpoint, that the old version remains in history and can be restored, that the response returns the forgotten memory, and that priority-3/core-guide memories require confirm=true. These are the exact behavioral facts an agent needs before mutating memory.

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?

Front-loaded with purpose, then the trigger, then the alternative, then consequences — a logical order with little waste. It is dense and the trailing confirm sentence is slightly appended rather than woven in, which keeps it from a perfect score.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, and the description compensates by explaining what the response returns (the forgotten memory) and the restorable checkpoint history. For a three-parameter destructive-adjacent tool, nothing an agent needs in order to call it correctly is missing.

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 coverage is 100%, so slug, reason and confirm are already documented in the schema itself. The description restates the confirm rule for critical memories and implies what reason feeds into (the checkpoint message), but adds no syntax or format detail beyond the schema. Baseline 3 applies when the schema does the heavy lifting.

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 opens with a specific verb and resource plus the effect: 'Remove a memory from the store so it is no longer recalled.' It also distinguishes itself from save_memory with supersedes, so an agent can tell which of the two mutation paths applies without inspecting either 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?

Usage is stated explicitly with a 'CALL THIS' trigger (wrong, obsolete, saved by mistake, nothing replaces it) and an explicit counter-case with the named alternative (if a newer memory replaces it, use save_memory with supersedes). Both the when and the when-not are covered.

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