Skip to main content
Glama
Sign In
madeleine

madeleine

by fabianimv
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

update_memory

Idempotent

Correct or annotate an existing memory by ID, updating content, tags, salience, metadata, or media reference while preserving omitted fields and sensory context.

Instructions

Correct or annotate an existing memory by id: its content, tags, salience, metadata or media_ref; omitted fields stay as they are, and tags/metadata are replaced, not merged. Use it when the user corrects a detail or when a memory turns out to matter more or less than first thought. The sensory context (when and where it happened, what was sensed) cannot be edited, because it records the moment of encoding; to change that, forget the memory and remember it again. If the content changes, text matching follows the new content. Returns the updated memory as JSON.

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": {
      "memory_id": "<memory_id>"
    },
    "name": "update_memory"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagsNoNew tags; replaces the current list. Omit to keep them.
contentNoNew text of the memory. Omit to keep the current one.
metadataNoNew string key/value annotations; replaces the current ones.
salienceNoNew significance, 0 (trivial) to 1 (life-changing). Omit to keep.
media_refNoNew pointer (URI/path) to related media; never opened.
memory_idYesThe memory's id (e.g. 'mem_0189a3f2c1d4_9f3c2a7b1e').

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.2.0

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare non-read-only, idempotent, non-destructive, closed-world. The description adds genuinely new behavior: omitted fields are preserved, tags/metadata are replaced rather than merged, sensory fields are immutable, and text matching follows updated content. Strong, though it doesn't state permission/auth expectations or how the id lookup fails.

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-loads the core action and the id, then layers in rules and the escape hatch. Every sentence carries information, though the middle section is dense with three distinct rules packed together; light restructuring could improve scanability.

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?

Covers the mutation semantics, the immutability boundary and its workaround, id format conventions via the schema, and explicitly states the return value ("updated memory as JSON") despite the absence of an output schema. Nothing an agent needs to invoke it correctly is missing.

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 baseline is 3. The description still adds semantics beyond the schema: the replace-not-merge rule for tags/metadata and the keep-if-omitted rule apply across all optional fields, and it explains why media_ref/sensory fields behave the way they do.

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?

Opens with a specific verb+resource: "Correct or annotate an existing memory by id", then enumerates the editable facets (content, tags, salience, metadata, media_ref). This clearly separates it from sibling create/delete tools such as remember and forget.

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?

Gives explicit triggers ("when the user corrects a detail or when a memory turns out to matter more or less") and an explicit exclusion with the alternative spelled out: the sensory context cannot be edited, so "forget the memory and remember it again" — naming the sibling tools to use instead.

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