Maindex Expert Memory Service

memory_unassociate

DestructiveIdempotent

Remove typed links between memories (inverse links auto-removed for known types). This is the unlink counterpart to memory_associate — it does not create links and does not soft-delete or restore memories. Idempotent — missing or already-deleted links appear in not_found. Provide link_ids OR from_memory_id + targets.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

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

Input Schema

Name	Required	Description
`signer`	No	Agent identity -- who wrote this. Required fields: agent_id, run_id.
`targets`	No	Target memories to unlink (triple mode)
`link_ids`	No	Link IDs to remove (preferred mode)
`from_memory_id`	No	Source memory ID (triple mode)

Output Schema

Name	Required	Description	Default
`removed`	Yes	Removed link objects
`not_found`	Yes	Link or target IDs that were not found

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 8, 2026

TDQS

A4.7/5.0

Behavior4/5

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

Annotations already declare destructive, idempotent and closed-world, but the description adds a real behavioral fact not in them: inverse links are auto-removed for known relation types, a cascade effect the agent would not otherwise expect. It also notes that missing/already-deleted links surface in not_found, which softens the destructive profile.

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?

Three dense sentences, each doing distinct work (scope, sibling routing, cascade, idempotency, argument modes), with the core action front-loaded. No filler.

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 nested-object mutation tool, the description covers cascade behavior, idempotency semantics, argument mode selection, and negative scope; return values are covered by the existing output schema, so nothing essential is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so field meanings are covered, but the description adds a cross-parameter constraint the schema does not enforce: 'Provide link_ids OR from_memory_id + targets.' That mode-selection rule is genuine value beyond the structured fields.

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?

Opens with a specific verb+resource ('Remove typed links between memories') and immediately distinguishes itself from the sibling memory_associate by naming it as the inverse counterpart.

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?

Explicitly routes the agent: use memory_associate to create links, this tool to unlink them; it also states you need link_ids OR from_memory_id + targets, so the mode choice is unambiguous. Exclusion from soft-delete/restore implies memory_forget for that job.

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?