The Graph

Forget

forget

DestructiveIdempotent

Delete a previously stored memory by key. Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier. Pair with remember and recall.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "key": "user_research_topic"
    },
    "name": "forget"
  }
}

Input Schema

Name	Required	Description
`k`	No	Alias for key.
`key`	Yes	Memory key to delete. Accepts name, k, label as aliases.
`name`	No	Alias for key.
`label`	No	Alias for key.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedSep 25, 2026

addedInput schema / properties / k

Added value: +{
+  "description": "Alias for key.",
+  "type": "string"
+}

changedInput schema / properties / key / description

Previous value: -"Memory key to delete"New value: +"Memory key to delete. Accepts name, k, label as aliases."

addedInput schema / properties / label

Added value: +{
+  "description": "Alias for key.",
+  "type": "string"
+}

addedInput schema / properties / name

Added value: +{
+  "description": "Alias for key.",
+  "type": "string"
+}

Changed1 schema field changedMay 26, 2026
- addedInput schema / examples
```
Added value: +[
+  {
+    "key": "user_research_topic"
+  }
+]
```
First observedMay 12, 2026

TDQS

A4.3/5.0

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 and write profile are covered. The description aligns with those hints but adds little behavioral context beyond the use cases; it does not, for example, state whether deleting a missing key is an error or what the response looks like. With annotations carrying the main burden, a 3 is appropriate and there is no contradiction.

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?

Two sentences with no filler: the core action and key-based scoping come first, followed directly by usage guidance and sibling pairing. Every sentence earns its place.

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 simple deletion tool with a fully documented schema, explicit destructive/idempotent annotations, and no output schema obligations, the description covers what an agent needs: what it deletes, when to use it, and how it relates to remember and recall. Nothing critical 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 description coverage is 100%, and the schema already explains that key, k, name, and label are aliases for the memory key. The description adds no parameter-level details, but since the schema fully documents the single meaningful parameter, it does not need to; baseline 3 is correct.

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-resource pair: 'Delete a previously stored memory by key.' It clearly distinguishes the tool from its siblings remember and recall by naming them and positioning forget as the deletion counterpart, so an agent can select it correctly without opening the 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?

The description gives explicit triggering conditions: 'Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier.' It also names the complementary tools remember and recall, routing the agent to its siblings and making the when-to-use decision unambiguous.

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

All The Graph tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.