Skip to main content
Glama

Update a memory in place

memory_update
Idempotent

Update specific fields of an existing memory to fix typos, retag, or adjust importance. Changes to content trigger re-embedding asynchronously.

Instructions

Edit a memory in place — only the fields you pass are changed. Editable: title, content, tags, importance, memory_type, pinned. Use for typo fixes, retagging, importance tuning. For meaningful changes you'd want history for (e.g. a reversed decision), prefer memory_store(supersedes_id=...) instead. Side effect: when content changes, the embedding is re-queued and dedup may run. Returns not found for missing ids.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
memory_idYesId of the memory to update (e.g. `mem_01HXYZ...`).
titleNoNew title (single line). Omit to leave unchanged.
contentNoNew body in markdown. Omit to leave unchanged. When changed, the embedding is re-computed asynchronously.
tagsNoReplacement tag list. Omit to leave unchanged. Pass `[]` to clear all tags.
importanceNoNew importance score in [0, 1]. Omit to leave unchanged.
memory_typeNoNew memory_type (e.g. `fact`, `decision`). Omit to leave unchanged.
pinnedNoNew pinned state. Omit to leave unchanged. Equivalent to calling `memory_pin` separately.
dedupNoPer-call override for duplicate handling when `content` changes. Mirrors `memory_store.dedup`.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
messageYes`Memory <id> updated.` on success, `Memory <id> not found.` when missing, or a dedup-rejection sentence when `dedup="strict"` blocks the change.
Behavior5/5

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

The description adds behavioral traits beyond annotations: side effect of embedding re-queuing and dedup on content change, and returns 'not found' for missing ids. Annotations already indicate idempotent and non-destructive, but description provides extra operational context.

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?

Two concise sentences front-loading the purpose, then guidelines and side effects. No unnecessary words.

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 all essential aspects: partial update, editable fields, side effects, alternative tool, and return behavior. With high schema coverage and output schema present, the description is complete.

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% with detailed param descriptions. The tool description adds the key semantic that only passed fields are changed (partial update) and references dedup as mirroring memory_store.dedup, which adds value beyond schema.

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 clearly states the tool edits a memory in place, lists the editable fields, and distinguishes it from memory_store which is for meaningful changes with history. This is specific and differentiates from 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?

The description explicitly tells when to use (typo fixes, retagging, importance tuning) and when not to use (meaningful changes needing history), and recommends the alternative memory_store(supersedes_id=...).

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/lfrmonteiro99/memento-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server