Skip to main content
Glama

Remove a fact from durable memory (writes + git-commit, gated)

memory_forget

Remove a single remembered fact from MEMORY.md after one-time approval, with the deletion git-committed so it remains recoverable. Use when a user asks to forget or correct a stored memory.

Instructions

Remove one entry from MEMORY.md (e.g. when the user says to forget/correct a remembered fact) and git-commit the removal — the fact stays recoverable from git history (not a hard delete). This is a GATED action: it pauses and shows the targeted entry for a one-time approval before removing; just call it (no separate confirm needed). match is a distinctive substring of the entry to remove; it refuses if zero or more than one entry matches (it will not guess).

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": {
      "match": "<match>"
    },
    "name": "memory_forget"
  }
}

Input Schema

NameRequiredDescriptionDefault
matchYesA distinctive substring of the single entry to remove (must match exactly one).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.1

TDQS

A4.4/5.0
Behavior5/5

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

With no annotations, the description carries the full behavioral burden and does so well: it discloses the write and git-commit behavior, that the removal is recoverable from git history rather than a hard delete, that a one-time approval gate interrupts execution, and that ambiguous matches are refused rather than guessed.

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 description is front-loaded with the core action and side effect, then covers gating and match semantics in a compact paragraph. Every sentence contributes useful information, including the example and the no-separate-confirm clarification.

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?

For a one-parameter mutation tool with no annotations and no output schema, the description covers the essential behavior: what is removed, how it is persisted, recoverability, approval gating, and ambiguous-match refusal. Nothing critical is missing for an agent to call it correctly.

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?

Schema coverage is 100%, so the schema already defines `match` as a distinctive substring matching exactly one entry. The description adds useful behavioral meaning beyond the schema by stating it refuses on zero or multiple matches and will not guess, which helps the agent understand failure modes.

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 states a specific verb and resource: remove one entry from MEMORY.md and git-commit the removal. It is clear and concrete, but it does not explicitly differentiate itself from nearby memory-editing siblings such as propose_brain_edit or commit_brain_edit.

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?

It gives a clear usage context, e.g. when the user says to forget or correct a remembered fact, and explains that the gated approval is handled internally so no separate confirmation call is needed. It does not name alternatives or explicitly state when another memory-editing tool would be preferred.

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