Skip to main content
Glama

Forget Memory

forget_memory
DestructiveIdempotent

Delete a specific memory by ID and remove its incident graph edges, keeping stored context accurate and preventing stale links from affecting recall.

Instructions

Delete a specific memory and its incident graph edges by ID.

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_memory"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesUnique memory ID to remove.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so safety is covered. The description adds genuine context beyond them by disclosing that the deletion cascades to incident graph edges, which tells the agent the blast radius is wider than a single row.

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?

One short sentence with the destructive scope front-loaded and no filler. Every clause contributes: the target, the cascade, and the lookup key.

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 description covers target and cascade side effects adequately. It is only marginally short on what a missing ID returns, though idempotentHint partially covers that.

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?

The single required parameter has 100% schema description coverage ('Unique memory ID to remove.'), so the schema already carries the semantics. The description's 'by ID' adds nothing further such as format or where to obtain an ID, making the baseline 3 appropriate.

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?

States a specific verb ('Delete') and resource ('a specific memory') plus the scope of the operation ('its incident graph edges by ID'). The 'by ID' phrasing implicitly separates it from the sibling delete_by_context, but no alternative is named explicitly.

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 only implied: the agent must infer it should be used when it already holds a memory ID rather than a context description. There is no explicit when-to-use, when-not-to-use, or named alternative such as delete_by_context.

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