Skip to main content
Glama

Forget from RAMen Memory

forget
DestructiveIdempotent

Delete memory notes that contain given words, or remove a saved thread by specifying 'thread: ' and its name.

Instructions

Delete what RAMen Memory keeps about something, when the user asks you to forget it: every note that contains the given words. To delete a saved thread, give 'thread: ' and its name.

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

Input Schema

NameRequiredDescriptionDefault
aboutYeswords the notes to delete contain, for example 'Lindqvist', or 'thread: wedding planning'

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the safety profile is covered. The description does add meaningful blast-radius detail: deletion is by substring match and removes 'every note' containing those words, meaning multiple notes can go at once. It does not say whether deletion is recoverable or what happens when no note matches, leaving a gap for a destructive tool.

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?

Two compact sentences with the core action and scope front-loaded, followed by the thread special case. The thread instruction is slightly terse and the quoted 'thread: ' with trailing space is a bit cryptic, but nothing is wasted.

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 single-parameter destructive tool whose annotations already carry the safety profile, the description covers the trigger, the matching rule, and the thread variant. Only recoverability and the no-match outcome are unaddressed, which is a small residual gap rather than a blocker.

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% and the sole parameter already documents the word-matching semantics and the 'thread: ' prefix example. The description reinforces the containment rule and the thread convention but adds no syntax or matching nuance beyond what the schema provides, so baseline 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 and resource ('Delete what RAMen Memory keeps about something') plus the exact matching rule ('every note that contains the given words'), which distinguishes it cleanly from recall/remember siblings. An agent can identify this as the deletion counterpart to the memory tools without opening any schema.

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?

Explicitly scopes usage to 'when the user asks you to forget it,' which is a clear trigger condition, and adds a special-case instruction for threads ('give "thread: " and its name'). It stops short of naming alternatives (e.g., recall for reading) or stating when not to use it, so it is clear context without full alternative routing.

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