SLayer

Overview Schema Source Related Servers Discussions Admin

forget_memory

Removes a memory by ID and cleans up any references to it from related memories, returning a clear error for invalid or missing IDs.

Instructions

Delete a memory by id.

Cascades: every other memory's memory:<id> reference to this id is automatically stripped from its entities list.

Args: id: The memory_id returned by save_memory. Accepts strings (the canonical form, including user-supplied "kb.policy"-style ids) as well as legacy ints (coerced to their decimal string form).

Raises a friendly error if the id is invalid or the memory does not exist.

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

Name	Required	Description	Default
`id`	Yes

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.10.0Sep 3, 2026

TDQS

A4.5/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and it discloses the key side effect (cascading removal of memory:<id> references from entities lists) and the error behavior for invalid or missing ids. It does not discuss reversibility or permissions, but the destructive action and cascade are clearly stated.

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?

The description is front-loaded with the core action, then efficiently explains cascade behavior, parameter formats, and error handling. No sentence is wasted, and the structure is scannable.

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 deletion tool with an output schema, the description covers the operation, parameter semantics, side effects, and errors. The only minor gap is that it does not describe the output or return value, but that is already covered by the output schema.

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

Parameters5/5

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

Schema coverage is 0% and the description fully compensates: it defines id as the memory_id returned by save_memory, lists accepted forms (canonical strings including kb.policy-style ids and legacy ints), and explains int coercion. This is more precise than the bare 'Id' property in the schema.

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?

States a specific action ('Delete a memory by id') with the exact resource and identifier. This clearly distinguishes it from sibling deletion tools like delete_model and delete_datasource because it targets memories.

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?

The description establishes clear context: use this when you have a memory_id from save_memory and need to remove that memory. It does not explicitly name alternatives or exclusions, but the resource distinction plus the save_memory relationship makes the appropriate use obvious.

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