Skip to main content
Glama
mergestorm-mcp

mergestorm-mcp

Official

Forget memory

forget_memory
DestructiveIdempotent

Delete a stored memory by its UUID when it is obsolete or the user asks to forget it.

Instructions

Forget a memory that no longer holds, or anything the user asks you to forget, by its id from list_memories or search_memory.

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

NameRequiredDescriptionDefault
idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.31

TDQS

A4.2/5.0
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 deletion semantics and repeat-safety are known from structured data. The description adds only the id provenance and the intent framing; it does not say whether the deletion is permanent or what happens when the id does not exist, which would be the valuable extra context.

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?

A single sentence, front-loaded with the action and intent, followed by the practical detail of where the id comes from. No filler or repetition of the tool name.

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 destructive tool with full annotation coverage and no output schema, the definition covers action, intent and id source, which is enough to invoke it. It stops short of describing post-deletion behavior (permanence, response, unknown id), the only remaining gap.

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 0%, so the schema only says 'string, uuid' for id. The description compensates by telling the agent where to obtain that id (list_memories or search_memory), which is the one non-obvious fact needed to call the tool correctly.

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 verb (forget/delete) and resource (a memory) and pins down the identifier source: 'by its id from list_memories or search_memory'. That immediately separates it from search_memory and list_memories, which are the lookup siblings, so an agent can pick the right tool 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 Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives two concrete conditions for use: the memory 'no longer holds' or 'the user asks you to forget'. It does not cover the obvious near-miss case — correcting stale content via update_memory rather than deleting it — so there is clear context but no explicit exclusion.

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