Skip to main content
Glama
phillipclapham

anneal-memory

by phillipclapham
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

record

Capture decisions, observations, tensions, or outcomes as typed episodes to build session memory for compression. Log the reasoning behind each entry, not just the fact.

Instructions

Record a typed episode to memory. Call this when important decisions are made, patterns are noticed, tensions are identified, questions arise, or outcomes are observed. Record the reasoning, not just the fact — 'Chose X because Y' is more valuable than 'using X'. Episodes accumulate during a session and serve as raw material for compression into the continuity file at session end.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sourceNoAgent or source attribution. Defaults to 'agent'.agent
contentYesThe episode content — what happened, what was observed, decided, or questioned.
metadataNoOptional JSON metadata to attach to the episode.
supersedesNoIds of older episodes this one replaces (a changed fact). Each must exist, not be newer, and share at least a quarter of the shorter text's meaningful words with this content; otherwise nothing is recorded. recall then hides the old episode by default.
episode_typeYesEpisode type. observation=pattern/insight, decision=committed choice, tension=conflict/tradeoff, question=open question, outcome=result of action, context=environmental/state info.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.9.23
    • addedInput schema / properties / supersedes
      Added value: +{
+  "description": "Ids of older episodes this one replaces (a changed fact). Each must exist, not be newer, and share at least a quarter of the shorter text's meaningful words with this content; otherwise nothing is recorded. recall then hides the old episode by default.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
  2. First observedv0.1.4

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and delivers key lifecycle context: episodes accumulate during a session and become raw material for the continuity file at session end. It also advises recording reasoning ('Chose X because Y'), which shapes behavior. It does not describe persistence guarantees, failure modes, or the id returned for later supersede/delete use.

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?

Three tightly front-loaded sentences: purpose, invocation triggers, and the reasoning-capture rule, closing with lifecycle context. Each sentence carries information, though the closing lifecycle sentence could be trimmed slightly.

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?

Covers purpose, triggers, content quality, and session lifecycle for a 5-param, nested-object tool with no output schema. The one gap is that it never mentions the returned episode id, which callers need for supersedes or delete_episode, but that is recoverable from sibling tools.

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; the description still adds value by framing the tool as recording a 'typed episode' and instructing that content capture reasoning rather than bare facts, which refines how the schema's content parameter should be filled.

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+resource ('Record a typed episode to memory') and implies the write-side counterpart to recall/delete_episode. An agent can tell it apart from the retrieval siblings without opening the 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?

Gives explicit triggers for when to call it (decisions made, patterns noticed, tensions identified, questions arise, outcomes observed). It lacks explicit when-not-to-use guidance and doesn't name recall/delete_episode as alternatives, but the context is clear enough to act on.

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