XMemo

Overview Schema Source Related Servers Discussions Admin

Recall XMemo memory

recall

Read-onlyIdempotent

Retrieve relevance-ranked memories from XMemo before answering, with time, path, type, and working-memory filters. Use for quick best-effort lookup when you need one or a few grounding memories.

Instructions

Recall a few relevance-ranked memories before answering, with path/type controls and optional working-memory preference. Use it for a quick best-effort lookup; use recall_context when the answer needs a bounded multi-memory context pack.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`limit`	No	Maximum number of results to return.
`query`	Yes	Natural-language question or search text.
`since`	No	RFC 3339 timestamp with timezone offset (e.g., '2026-09-01T00:00:00+09:00'). Trigger: Call this whenever the user query mentions any relative or absolute time constraint in any language (e.g., today, yesterday, last week, last month, recently, Aug 1, Aug 10 to Sep 1, since Monday, before Sep 15, in Q3). Model responsibility: You (the calling LLM) know current date and user local time, so you must convert natural language time expressions into absolute timestamps. Consequence: If omitted, the server falls back to heuristic guessing which may misinterpret timezone day boundaries or relative dates.
`until`	No	RFC 3339 timestamp with timezone offset (e.g., '2026-09-02T00:00:00+09:00'). When used with since, defines the half-open interval [since, until) with until > since (maximum 90 days span). Trigger: Pass when the user query specifies an end date or bounded window in any language (e.g., yesterday end of day, by Aug 10, Aug 10 to Sep 1). Model responsibility: Convert natural language end bounds into absolute timestamps with timezone offsets. Consequence: If omitted, the window is open-ended on the upper side or derived heuristically.
`explain`	No	Whether to include retrieval explanation details with search or recall results.
`agent_id`	No	Optional client-supplied agent label for memory attribution.
`query_mode`	No	Optional query intent: 'topic' (default) or 'activity_log'. Trigger: Set 'activity_log' for event feeds within a bounded [since, until) window; set 'topic' for topic retrieval. Model responsibility: 'activity_log' requires explicit bounded 'since' and 'until' timestamps. Consequence: 'activity_log' without bounds fails closed; explicit 'topic' blocks stream bypass.
`time_order`	No	Sort order for returned memories: 'desc' (newest first) or 'asc' (oldest first). Trigger: Pass 'desc' when the user asks for 'latest', 'recent', 'newest first', or recency, or 'asc' for chronological order ('oldest first') in any language. Model responsibility: Explicitly set desired temporal ordering when the user expresses recency intent. If omitted and since/until are omitted, default relevance ranking is used without temporal sorting.
`memory_type`	No	Memory type/category filter or value, such as episodic, identity, procedural, semantic, working, auto, or %.	%
`path_filter`	No	Memory path filter; % matches all paths.	%
`owner_timezone`	No	The user's real IANA timezone, such as Asia/Tokyo or America/Los_Angeles. Required for honest calendar periods; never guess UTC.
`prefer_working`	No	Whether to prioritize working/session-state memories in retrieval.
`reference_time`	No	Optional ISO 8601 reference time snapshot for deterministic evaluation. Leave blank to use the real clock; setting this does not replace owner_timezone for calendar day boundaries.
`agent_instance_id`	No	Optional stable, non-secret agent instance ID for per-client attribution.
`temporal_axis_mode`	No	Input value for the Recall tool.
`hypothetical_answer`	No	Input value for the Recall tool.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed8 schema fields changedv0.4.186Sep 8, 2026

addedInput schema / properties / hypothetical_answer

Added value: +{
+  "default": "",
+  "description": "Input value for the Recall tool.",
+  "title": "Hypothetical Answer",
+  "type": "string"
+}

addedInput schema / properties / owner_timezone

Added value: +{
+  "default": "",
+  "description": "The user's real IANA timezone, such as Asia/Tokyo or America/Los_Angeles. Required for honest calendar periods; never guess UTC.",
+  "title": "Owner Timezone",
+  "type": "string"
+}

addedInput schema / properties / query_mode

Added value: +{
+  "default": "",
+  "description": "Optional query intent: 'topic' (default) or 'activity_log'. Trigger: Set 'activity_log' for event feeds within a bounded [since, until) window; set 'topic' for topic retrieval. Model responsibility: 'activity_log' requires explicit bounded 'since' and 'until' timestamps. Consequence: 'activity_log' without bounds fails closed; explicit 'topic' blocks stream bypass.",
+  "title": "Query Mode",
+  "type": "string"
+}

addedInput schema / properties / reference_time

Added value: +{
+  "default": "",
+  "description": "Optional ISO 8601 reference time snapshot for deterministic evaluation. Leave blank to use the real clock; setting this does not replace owner_timezone for calendar day boundaries.",
+  "title": "Reference Time",
+  "type": "string"
+}

addedInput schema / properties / since

Added value: +{
+  "default": "",
+  "description": "RFC 3339 timestamp with timezone offset (e.g., '2026-09-01T00:00:00+09:00'). Trigger: Call this whenever the user query mentions any relative or absolute time constraint in any language (e.g., today, yesterday, last week, last month, recently, Aug 1, Aug 10 to Sep 1, since Monday, before Sep 15, in Q3). Model responsibility: You (the calling LLM) know current date and user local time, so you must convert natural language time expressions into absolute timestamps. Consequence: If omitted, the server falls back to heuristic guessing which may misinterpret timezone day boundaries or relative dates.",
+  "title": "Since",
+  "type": "string"
+}

addedInput schema / properties / temporal_axis_mode

Added value: +{
+  "default": "",
+  "description": "Input value for the Recall tool.",
+  "title": "Temporal Axis Mode",
+  "type": "string"
+}

addedInput schema / properties / time_order

Added value: +{
+  "default": "",
+  "description": "Sort order for returned memories: 'desc' (newest first) or 'asc' (oldest first). Trigger: Pass 'desc' when the user asks for 'latest', 'recent', 'newest first', or recency, or 'asc' for chronological order ('oldest first') in any language. Model responsibility: Explicitly set desired temporal ordering when the user expresses recency intent. If omitted and since/until are omitted, default relevance ranking is used without temporal sorting.",
+  "title": "Time Order",
+  "type": "string"
+}

addedInput schema / properties / until

Added value: +{
+  "default": "",
+  "description": "RFC 3339 timestamp with timezone offset (e.g., '2026-09-02T00:00:00+09:00'). When used with since, defines the half-open interval [since, until) with until > since (maximum 90 days span). Trigger: Pass when the user query specifies an end date or bounded window in any language (e.g., yesterday end of day, by Aug 10, Aug 10 to Sep 1). Model responsibility: Convert natural language end bounds into absolute timestamps with timezone offsets. Consequence: If omitted, the window is open-ended on the upper side or derived heuristically.",
+  "title": "Until",
+  "type": "string"
+}

First observedv0.4.176Jun 29, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare the tool read-only, idempotent, and non-destructive. The description adds useful behavioral context beyond that: results are relevance-ranked and the lookup is best-effort, implying the result set may not be exhaustive. This is meaningful without contradicting annotations.

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 compact sentences with no filler. The core behavior and scope are front-loaded, and the alternative-tool guidance is included efficiently. Every sentence earns its place.

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?

Given the tool's high parameter count, the description is brief but sufficient because the schema is fully documented and an output schema exists. It orients the agent to the tool's role and distinguishes it from the closest sibling, while the schema carries the detailed parameter semantics. A little more context about return-value shape or time-based behavior would be nice but is not necessary.

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 description coverage is 100%, and the schema already provides rich per-parameter semantics including triggers and consequences. The description mentions path/type controls and working-memory preference, which aligns with parameters, but it does not add meaning beyond what the schema already documents. Baseline 3 is appropriate.

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 identifies the action (recall a few relevance-ranked memories), the resource (XMemo memory), and the intended context (before answering). It also distinguishes itself from the sibling recall_context by naming it explicitly, so an agent can tell them apart.

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 gives explicit usage guidance: use recall for a quick best-effort lookup, and use recall_context when a bounded multi-memory context pack is needed. This is a clear when-to-use / when-not-to-use distinction with a named alternative.

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