Skip to main content
Glama

save_memory

Store lasting user memories across sessions, filtered by a quality gate to keep only important state like identity, projects, or preferences.

Instructions

Save a durable memory about the user through the Jamgate quality gate. Only call this for things worth remembering across sessions — identity, projects, preferences, lasting state — not chatter. Trivial or duplicate input is rejected by the gate.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
textYesThe memory, as a clear standalone statement. Canonical field — always prefer it; `content` and `memory` are accepted as aliases for clients that send the memory under another name.
typeNoWhich memory layer this belongs to (RULES §4).
scopeNoOptional namespace to save into, e.g. 'amir/greek'. Memories in different scopes never interfere — the gate (dedup, supersession, conflict) applies per scope, and recall/forget are per scope. Omit for the single default namespace, which is the normal single-user behaviour.
sourceNoWhere this memory came from. Defaults to agent-inferred.
subjectNoWhat this memory is about, e.g. 'operating-system', 'location', 'current-project'. If a newer memory shares a subject with an older one, the newer replaces it (time-aware supersession). ALWAYS pass this when the memory updates something already tracked — a progress figure, a balance, a status, a current choice — and reuse the EXACT subject string the earlier memory used. Without a matching subject the gate cannot tell an update from a new fact and both stay active. If omitted, the gate derives a best-effort subject from the text, and declines to guess when the text is long or covers several topics.
Behavior3/5

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

The description notes persistence and a quality gate but lacks detail on durability guarantees, what qualifies as trivial, or side effects. With no annotations, it does not fully disclose behavioral traits.

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 two sentences, front-loaded with the action and context, with no redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 5 parameters and no output schema, the description fails to mention return values or success/failure indicators. It provides adequate purpose but lacks completeness for a full understanding.

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 coverage is 100%, baseline 3. Description adds value by noting text aliases ('content', 'memory') and the gate's role, but does not substantially expand parameter meaning.

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 saves a durable memory, distinguishes it from chatter, and references a quality gate. It contrasts with siblings recall_memory and forget_memory by focusing on 'things worth remembering across sessions'.

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?

Explicitly advises when to use ('identity, projects, preferences, lasting state') and when not ('chatter'). Mentions the gate rejects trivial/duplicate input. However, it does not directly compare with sibling tools recall and forget.

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/amirj4m/jamgate'

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