Skip to main content
Glama
phasespace-labs

palinode

by phasespace-labs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

palinode_forget_withdraw

DestructiveIdempotent

Withdraw a prior forget request to restore archived memories, un-retract mentions, and archive the request record; each change is audited per target.

Instructions

Take a forget request back. Given the memory that holds the request ('please forget that I…'), restores every memory it archived, un-strikes every mention it retracted, and archives the request record(s) so they stop acting as the retraction. Each step is its own audited commit; failures are reported per target.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
reasonNoWhy the request is being withdrawn (kept in the audit trail).
dry_runNoPreview what would change, the retained copies and the recovery command; write nothing.
file_pathYesPath of the memory holding the forget request (e.g., 'insights/forget-sneakers.md')

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.22.0
    • addedInput schema / properties / dry_run
      Added value: +{
+  "default": false,
+  "description": "Preview what would change, the retained copies and the recovery command; write nothing.",
+  "type": "boolean"
+}
  2. Addedv0.17.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so safety is partly covered. The description adds meaningful behavior beyond that: it is a multi-step composite, each step is an audited commit, and failures are reported per target. What it does not cover is whether partial success leaves the system in an intermediate state or how recovery works on failure.

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 the single-sentence purpose, then the mechanics, then the commit/failure semantics. Every sentence carries information and there is no padding, though the final clause about per-target failures is slightly dense.

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 destructive, multi-step mutation with no output schema, the description is largely sufficient: it explains what is touched, that work is committed in audited steps, and how failures surface. It could go further on permission requirements and the resulting state after a partial failure, but the core is covered.

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% across all three parameters, so the schema already documents file_path, reason and dry_run semantics. The description adds no parameter-level meaning beyond that, so the baseline 3 applies.

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?

States a specific verb+resource ('Take a forget request back') and then enumerates exactly what it does: restores archived memories, un-strikes mentions, archives the request record. That is far more specific than a tautology. It stops short of a 5 because it never names the closely related siblings (palinode_restore, palinode_unretract, palinode_archive) that an agent might otherwise reach for.

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 'Given the memory that holds the request' plus the parenthetical example implies the entry condition, but there is no explicit when-to-use vs when-not guidance and no mention of alternatives for partial undo (e.g., using restore/unretract individually). Usage is implied rather than stated.

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