Skip to main content
Glama
dreamforgestudiollc

EMET

by dreamforgestudiollc
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Hybrid

revise_memory

Supersede an existing memory entry with a revised version, creating a new linked entry so the original remains available alongside the update.

Instructions

Supersede an existing entry with a revised one (supersession, not mutation). Creates a NEW entry carrying metadata.supersedes= and marks the target entry metadata.superseded_by=. Superseded entries STILL SURFACE in recall / query_layer / semantic_recall, marked with superseded_by and is_superseded, so the revision is read alongside what it replaced (query_layer options.include_superseded=false gives the live-only view). Episodic revision is prohibited - events are immutable.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
layerYesLayer of the entry being revised (episodic is prohibited)
contentYesFull revised content - must stand alone without the superseded entry
exchangeNoThe exchange (turn) this write belongs to, counting from 1. A write for exchange n while exchange n-1 was never appended is refused by the session graph until n-1 is appended.
metadataNoMetadata for the new entry (supersedes is set automatically; include source tag)
target_idYesID of the entry this revision supersedes
session_idNoYour transcript session id from emet_session_open. The session graph reads this session's state before the write and returns `session_graph.next` - the next step. A governed write with no session is refused (open one with emet_session_open and load_id).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.2.2
    • changedInput schema / properties / exchange / description
      Previous value: -"The exchange (turn) this write belongs to, counting from 1. A write for exchange n while exchange n-1 was never appended is flagged by the session graph."New value: +"The exchange (turn) this write belongs to, counting from 1. A write for exchange n while exchange n-1 was never appended is refused by the session graph until n-1 is appended."
    • changedInput schema / properties / session_id / description
      Previous value: -"Your transcript session id from emet_session_open. The session graph reads this session's state before the write and returns `session_graph.next` - the next step."New value: +"Your transcript session id from emet_session_open. The session graph reads this session's state before the write and returns `session_graph.next` - the next step. A governed write with no session is refused (open one with emet_session_open and load_id)."
  2. First observedv0.1.0

TDQS

A4.5/5.0
Behavior5/5

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

No annotation contradiction: destructiveHint=false is actively supported by the disclosure that superseded entries still surface in recall/query_layer/semantic_recall marked with superseded_by and is_superseded, while idempotentHint=false aligns with each revision minting a new id. The description goes well beyond the annotations by disclosing the exact write mechanics (new entry carrying metadata.supersedes, target marked metadata.superseded_by), the read-visibility consequence, and the immutability constraint on episodic.

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?

Front-loaded with the core semantics in the first sentence, then layers in write mechanics, read visibility, and the prohibition in tight, non-redundant sentences. Every sentence carries distinct information an agent needs.

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 six-parameter, non-idempotent write with no output schema, the description is complete: it explains the effective outcome (a new id plus a superseded target), how superseded content remains visible to readers, and the immutability carve-out. Nothing an agent needs to invoke this 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%, and the schema already documents layer, content, exchange, metadata, target_id and session_id in detail (including the session-graph refusal behavior). The description adds the constraint 'episodic is prohibited' echoed from the schema, but contributes no additional syntax or format meaning to the parameters, so the baseline 3 applies.

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 a specific verb+resource and immediately disambiguates the operation: 'Supersede an existing entry with a revised one (supersession, not mutation).' It distinguishes this from mutation-style updates and from creation by naming the mechanics (new entry + metadata.supersedes), so an agent can tell it apart from save_to_layer or patch-style siblings without opening a schema.

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

Usage Guidelines4/5

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

It clearly states the condition for use (revising an existing entry rather than creating one) and an explicit exclusion ('Episodic revision is prohibited - events are immutable'), plus the read-side alternative (query_layer options.include_superseded=false for the live-only view). It stops short of explicitly naming the sibling to use for a fresh write (e.g., save_to_layer), so this is clear context rather than full when/when-not/alternatives routing.

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