Skip to main content
Glama
Sign In
Monomem

Monomem

by calasdan-sketch
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Step 2 of replacing a memory: do it

memory_supersede_confirm
Destructive

Confirms a previewed note replacement only after the user reads the warning and approves, using a one-time token that fails if any note changed.

Instructions

STEP 2. Replaces the note(s) previewed with memory_supersede_preview, but ONLY with that preview's one-time token and ONLY after the person has read the warning and said yes. The token expires, works once, and fails if any note changed since the preview, so nothing is replaced by surprise. If you previewed a NEW note (new_title), send the same new_title/new_body/new_tags/new_confidence again. Nothing is deleted: the old note is kept, marked superseded, and memory_supersede_undo brings it back. If the warning had a RED FLAG, an admin connection must also pass acknowledge_risk: true.

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": {
      "token": "<token>"
    },
    "name": "memory_supersede_confirm"
  }
}

Input Schema

NameRequiredDescriptionDefault
tokenYesThe confirmation code from memory_supersede_preview.
new_bodyNoThe text of the new note.
new_tagsNoTags for the new note.
new_titleNoThe title of the NEW note that will take the old note's place. Give this (with new_body) OR new_id.
new_confidenceNoOptional CLAIM (0 to 1) of how sure you are of the new note. A claim only.
acknowledge_riskNoOnly for a warning that had a RED FLAG: say you accept it (admin connections only).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.3.4

TDQS

A4.8/5.0
Behavior5/5

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

Goes far beyond destructiveHint=true by disclosing token expiry, single-use semantics, a staleness guard that fails if any note changed, and the admin-only acknowledge_risk requirement. It also clarifies the blast radius — the old note is retained and marked superseded rather than deleted, and undo restores it.

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?

Front-loaded with 'STEP 2' and every sentence carries a distinct constraint (token, confirmation, expiry, resend, reversibility, red flag). Dense and heavily capitalized emphasis make it read as a run-on, but there is 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 6-parameter irreversible-looking mutation with no output schema, the description covers preconditions, failure modes, side effects, recovery path, and elevated-permission path. An agent has everything needed to call it safely.

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 the baseline is 3, but the description adds workflow meaning: the new_* fields must be re-sent verbatim when a new note was previewed, and acknowledge_risk is conditional on a RED FLAG plus an admin connection. That is genuine guidance beyond the field-level descriptions, though acknowledge_risk is largely restated.

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 ('Replaces the note(s) previewed with memory_supersede_preview') and frames itself as STEP 2 of an explicit two-step workflow, so it is immediately distinguishable from the preview and undo siblings.

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 gates invocation: only with the preview's one-time token, and only after the person has read the warning and said yes. It also routes backward to memory_supersede_preview and forward to memory_supersede_undo, leaving no inference required.

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

Deploy Server

Other Tools