MemScope

Forget memory

forget_memory

DestructiveIdempotent

Use this only when the person asks to forget a memory. For an outdated or duplicated one, use supersede_memory (keeps it, linked) or ask the person. Nobody recalls it any more; restore_memory brings it back during the trash period (30 days by default), then its content is erased for good. Forgetting it again returns not-found.

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": {
      "memory_id": "<memory_id>",
      "reason": "<reason>"
    },
    "name": "forget_memory"
  }
}

Input Schema

Name	Required	Description
`agent`	No	Your agent label.
`reason`	Yes	Why, for the audit; ask the person if unsure.
`run_id`	No	Your run id.
`memory_id`	Yes	Memory id ('mem_' prefix optional).
`confirm_human`	No	True only if the person asked or agreed to forget it.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedNov 8, 2026

removedInput schema / properties / reason / anyOf

Removed value: -[
-  {
-    "maxLength": 500,
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

removedInput schema / properties / reason / default
```
Removed value: -null
```

changedInput schema / properties / reason / description

Previous value: -"Why, kept in the audit trail. Up to 500 characters."New value: +"Why, for the audit; ask the person if unsure."

addedInput schema / properties / reason / maxLength
```
Added value: +500
```
addedInput schema / properties / reason / type
```
Added value: +"string"
```

changedInput schema / required

Previous value: -[
-  "memory_id"
-]New value: +[
+  "memory_id",
+  "reason"
+]

First observedNov 7, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds what they cannot: a 30-day trash window, that `restore_memory` can resurrect it in that period, that content is then erased permanently, and that a repeat call yields not-found. The audit purpose of `reason` is also surfaced behaviorally rather than left implicit.

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?

Four short sentences, front-loaded with the restrictive condition before the alternatives and consequences. Every clause carries information: the gate, the sibling routing, the recovery window, and the terminal failure mode. Nothing is repeated from the name or annotations.

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 destructive, restorable mutation this covers the full picture an agent needs: permission gate, escalation path, reversibility window, permanence, and post-purge behavior. An output schema exists, so the absence of return-value detail is not a gap.

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%, so the schema already documents memory_id, reason, confirm_human, agent, and run_id; the description adds no syntax, format, or constraint detail beyond what is there. 'Ask the person if unsure' and 'only when the person asked' loosely reinforce confirm_human, but that is alignment rather than new meaning, so the 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?

Names the specific action and resource ('forget a memory') and immediately clarifies the semantics that the verb alone obscures: it is a move-to-trash, not an immediate purge. It explicitly contrasts with `supersede_memory` and `restore_memory`, so an agent can distinguish it from every nearby sibling without opening a 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?

Gives a hard gate ('Use this only when the person asks to forget a memory') plus named alternatives for the adjacent cases: `supersede_memory` for outdated or duplicated memories, and 'ask the person' when intent is unclear. This is explicit when/when-not guidance with routing to siblings rather than inferred usage.

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

All MemScope 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.

Resources

Need Help?