Maindex Expert Memory Service

memory_forget

DestructiveIdempotent

Soft-delete a memory (sets status to 'deleted'; restorable). Mutates. Idempotent — safe to retry. Returns the deletion result with the memory's id and shortId. To undelete, use memory_update on the deleted id (any successful revision restores it and sets restoredFromDeleted on the response) or REST POST /v1/memories/:id/restore.

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>"
    },
    "name": "memory_forget"
  }
}

Input Schema

Name	Required	Description	Default
`signer`	No	Agent identity -- who wrote this. Required fields: agent_id, run_id.
`memory_id`	Yes	ID of the memory to delete

Output Schema

Name	Required	Description
`id`	No	Memory UUID
`deleted`	Yes	Whether the memory was deleted
`shortId`	No	Memory short ID

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 8, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Annotations only say destructiveHint=true and idempotentHint=true; the description does the harder work of clarifying that 'destructive' here is actually reversible (soft delete) and spelling out the exact restore mechanism including the restoredFromDeleted marker on the response. That is precisely the behavioral context an agent needs before calling a destructive-flagged tool.

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 essential fact (soft delete, restorable) before the recovery instructions. No filler and no repetition of the tool name.

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 single-target mutation tool with an output schema and full annotation coverage, this covers the remaining gap: reversibility and recovery. An agent has everything needed to decide to call it and what to do afterward.

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%, including a description for memory_id and the nested signer object, so the schema already carries parameter meaning. The description adds nothing about memory_id format or the signer object, which is acceptable given full coverage but is a baseline 3.

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 — soft-delete a memory — and immediately defines what 'delete' means here (status set to 'deleted', restorable). It does not, however, differentiate this from sibling memory_supersede, which is the other tool that removes a memory from active use.

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 clear operational context: this mutates, it is safe to retry, and it names the exact path back (memory_update on the deleted id, or the REST restore endpoint). What's missing is any guidance on when to forget versus supersede or update, so an agent still has to infer the boundary between siblings.

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

All Maindex Expert Memory Service 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?