mazarbul

Overview Schema Source Related Servers Discussions Admin

remember

Persist user facts, preferences, decisions, and corrections to durable long-term memory so agents can recall them beyond the current conversation.

Instructions

Persist a fact to the user's long-term memory. CALL THIS whenever the user tells you something about themselves, their work, their preferences, decisions, plans, or corrects a prior fact, even if you think you'll remember it within the current conversation. Mazarbul is the durable store; your own context is not. Pass the original sentence verbatim. remember stores and indexes the text for recall; entities and relations are extracted server-side only when a chat model is configured (usually not), so write the structure you see yourself with createEntity, relate, and fact.

Input Schema

Name	Required	Description
`text`	Yes	Natural-language record to remember. Stored verbatim as the Episode text.
`actor`	No	Who said it. "user" (the human), "assistant" (the AI agent), or "system". Defaults to "user" when omitted. Assistant-actor episodes are routed through a different extractor branch so AI-generated facts ("I've booked your flight for March 3rd") become first-class memories instead of being filtered as third-party narration.
`scope`	No	Sync / encryption boundary for the Episode. "personal" (default) is local-only; "project" is in-repo; "team" is shared under the team key; "draft" is private staging — invisible to recall until promoted via the CLI (maz scope draft promote); there is no listed MCP tool for draft promotion. Omit for the personal default.
`source`	No	Optional. Where the Episode originated (free-form, e.g. "cli:remember", "providers/anthropic"). Defaults to "mcp:remember" when omitted — just call remember({text}) for an ordinary fact.
`confidence`	No	Writer's confidence in the Episode. Range 0..1 inclusive. Defaults to 1.0 when omitted.
`coordinates`	No	Optional geographic coordinates (WGS84) associated with this Episode. When present, the resolver forwards them onto any matched or created place Entity.
`coordinatesProvenance`	No	Origin of the coordinates, e.g. user_provided or geocoded:nominatim. Required when coordinates is set; rejected when coordinates is absent.

Output Schema

Name	Required	Description	Default
`name`	Yes	AIP resource name of the created Episode: "episodes/{uid}".

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 31, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations are empty, so the description carries the full burden and does well: it discloses that storage is durable and verbatim, that indexing feeds recall, and — critically — that entity/relation extraction is conditional on a chat model being configured. Missing: nothing on deduplication/overwrite behavior or failure modes, which matters for a persistence tool.

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-loaded action statement followed by trigger, rationale, and the structural-write fallback — each sentence does work. The final clause is dense and runs long, but no sentence is expendable.

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 7-param write tool with an output schema, the description covers what the schema cannot: when to call, that writes are durable rather than conversational, and that automatic graph extraction usually will not happen so the agent must call the structural siblings itself. Nothing needed 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.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents all seven parameters including scope boundaries and the coordinates/coordinatesProvenance coupling. The description only reinforces the `text` argument ("Pass the original sentence verbatim"), which the schema already states, so it adds little beyond the baseline.

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?

Specific verb plus resource ("Persist a fact to the user's long-term memory") with clear scope. It also implicitly distinguishes itself from retrieval siblings (recall, get) and from structural writers (createEntity, relate, fact) by naming them.

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 an explicit, enumerated trigger list (user facts, preferences, decisions, plans, corrections) plus an anti-exclusion ("even if you think you'll remember it within the current conversation"). It also names the alternatives — createEntity, relate, fact — and the condition that selects them, namely that server-side extraction usually does not run.

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