Skip to main content
Glama

memory_delete

DestructiveIdempotent

Delete stored memories by IDs, key, or an exact-match query, with undo support. Use it to remove outdated facts, commands, or decisions from global or project memory.

Instructions

Delete by ids, key, or a query matching exactly one. Undoable.

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_delete"
  }
}

Input Schema

NameRequiredDescriptionDefault
idsNo
keyNo
queryNo
scopeNofor key; default project then global

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

A3.6/5.0
Behavior4/5

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

The annotations already declare destructiveHint=true and idempotentHint=true, so the description's job is to add context — and "Undoable" does exactly that, telling the agent deletions can be reversed and lowering the risk of using the tool. It stops short of saying how undo works or how long the window lasts.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with the verb and the selector list, with the undo guarantee placed second. Nothing is wasted, though the extreme terseness leaves the combination rules unstated.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive, zero-required-parameter tool with no output schema, the definition covers selection modes and reversibility but omits error behavior (no match / multiple matches), whether scope applies beyond key, and what a successful delete returns.

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?

With only 25% schema description coverage, the description must carry the load; it usefully maps three of four parameters to selection modes and constrains query to a single match. However, it says nothing about scope (documented in the schema as applying to key only) or about mutual exclusivity when several selectors are supplied.

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 opens with a specific verb, "Delete", and enumerates the three selection modes (ids, key, query), which lets an agent distinguish this from memory_search and memory_save. It never names a sibling or states the resource explicitly, so it falls short of full differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

The phrase "a query matching exactly one" is a real usage constraint that tells the agent when a query selector is acceptable, but there is no guidance on choosing between ids, key, and query, nor on what happens when zero or multiple records match.

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