PseudoLife-MCP

Official

Overview Schema Source Related Servers Discussions Admin

memory_forget

Remove or retire outdated, incorrect, or test data from memory, fact, world, or lesson stores. Hard-delete junk memories or facts, or retire world facts and lessons with an audit trail, preserving history.

Instructions

Forget from one memory store. memory and fact hard-delete (cleanup for junk/test data — no audit trail); world and lesson RETIRE the slot with an audit row, undone by memory_graph_review( action="restore_slot"). For "now wrong, keep history" use memory_fact_set (facts) or memory_supersede (memories) instead.

scope="memory" needs at least one of text/substring/ source/episode/tag, and those OR-combine — ANY match deletes, unlike memory_search's AND. The other scopes need entity.

Returns: {deleted_count | removed, ...}; {error} on bad input.

Input Schema

TableJSON Schema

Name	Required	Description
`tag`	No	memory scope: delete entries carrying this tag.
`text`	No	memory scope: delete entries whose text matches this exactly.
`scope`	Yes	Which store to delete from.
`entity`	No	fact/world scope: the slot's subject. lesson scope: the task.
`source`	No	memory scope: delete entries with this source tag.
`episode`	No	memory scope: delete entries stamped with this episode id.
`attribute`	No	fact/world scope: one slot's attribute; omit to purge the whole entity. lesson scope: the aspect.
`substring`	No	memory scope: delete entries whose text contains this.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed8 schema fields changedv0.15.0Sep 3, 2026

addedInput schema / properties / attribute / description

Added value: +"fact/world scope: one slot's attribute; omit to purge the whole entity. lesson scope: the aspect."

addedInput schema / properties / entity / description

Added value: +"fact/world scope: the slot's subject. lesson scope: the task."

addedInput schema / properties / episode / description

Added value: +"memory scope: delete entries stamped with this episode id."

addedInput schema / properties / scope / description
```
Added value: +"Which store to delete from."
```

addedInput schema / properties / source / description

Added value: +"memory scope: delete entries with this source tag."

addedInput schema / properties / substring / description

Added value: +"memory scope: delete entries whose text contains this."

addedInput schema / properties / tag / description

Added value: +"memory scope: delete entries carrying this tag."

addedInput schema / properties / text / description

Added value: +"memory scope: delete entries whose text matches this exactly."

First observedv0.11.0Jul 31, 2026

TDQS

A5/5.0

Behavior5/5

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

With no annotations provided, the description carries the full behavioral burden. It discloses that memory/fact entries are hard-deleted with no audit trail, world/lesson slots are retired with audit rows, that retirement is undone via memory_graph_review, and that ANY matching criterion deletes. This is substantial beyond what the schema 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?

The description is dense but every sentence earns its place: primary action, scope-specific destructive behavior, alternatives, matching semantics, and return/error shape. It is front-loaded with the core purpose and contains 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 an 8-parameter, four-scope destructive tool, the description covers scope behavior, conditional parameters, audit implications, undo path, alternatives, and return values. With an output schema present, no critical operational information is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the description adds critical parameter interplay: scope='memory' requires at least one of text/substring/source/episode/tag and these OR-combine, while other scopes require entity. This is exactly the kind of conditional semantics an agent needs and cannot infer from the schema alone.

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?

The description opens with 'Forget from one memory store,' naming a specific verb and resource. It then distinguishes hard-delete vs. retire semantics across scopes and explicitly contrasts with memory_fact_set and memory_supersede, making the tool's purpose clear relative to 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?

It explicitly states when to use alternatives: for 'now wrong, keep history' use memory_fact_set or memory_supersede instead. It also gives scope-specific parameter requirements and contrasts memory_forget's OR-combining matches with memory_search's AND behavior, giving clear selection guidance.

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