Skip to main content
Glama
persistent-memory-mcp

persistent-memory-mcp

Withdraw an artifact

memory_withdraw
DestructiveIdempotent

Withdraw an artifact the user marks as wrong, outdated, or forgotten; stop serving it and dependent items, notify sessions that saw it, and keep the reason in history.

Instructions

Stop serving an artifact the user says is wrong, outdated or must be forgotten, together with everything derived from it; sessions that saw them are notified. The text is not physically erased and the history keeps the reason. Run memory_plan_withdrawal first when the user should see what it blocks. To replace a text with a better one, use memory_correct instead.

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": {
      "artifact_id": "<artifact_id>",
      "reason": "<reason>"
    },
    "name": "memory_withdraw"
  }
}

Input Schema

NameRequiredDescriptionDefault
reasonYesWhy, in the user's words.
event_idNoOptional key; repeating a call with the same key changes nothing.
artifact_idYesThe artifact_id returned when it was stored or found by memory_search.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds the crucial nuance that the operation is a soft withdrawal — 'The text is not physically erased and the history keeps the reason.' It further discloses cascading effects ('everything derived from it') and the side effect of notifying affected sessions, which no annotation conveys.

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 sentences, each earning its place: what happens, what does not happen (soft delete), and how to proceed. Lead sentence is front-loaded with the action and scope, and the routing hints are compact rather than repetitive.

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?

Despite being a destructive, cascading mutation with no output schema, the description covers reversibility, audit trail, downstream effects, prerequisite preview, and the replacement alternative. Nothing an agent needs to invoke it safely is missing.

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%, so artifact_id, reason, and event_id are already fully documented in the schema, including the idempotency-key semantics. The description adds no parameter-level detail such as what artifact_id formats are accepted or how broad the derived-artifact set can be. Baseline 3 is appropriate when the schema carries the full burden.

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 and resource — 'Stop serving an artifact' — and immediately qualifies the scope as 'together with everything derived from it.' It distinguishes itself from memory_correct (replacement) and memory_plan_withdrawal (preview), so an agent can route correctly without opening other schemas.

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?

Gives an explicit prerequisite ('Run memory_plan_withdrawal first when the user should see what it blocks') and an explicit alternative ('To replace a text with a better one, use memory_correct instead'). Both the when-to-use and the when-to-use-something-else cases are covered.

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