Skip to main content
Glama

XMemo

by io.github.yonro

Search XMemo memories

search_memory
Read-onlyIdempotent

Search XMemo memories with strong-match semantics. Use it for a targeted lookup where weak matches must not be returned as answers; use recall for forgiving best-effort retrieval or recall_context for a bounded multi-memory context pack. To delete a memory, use forget.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum number of results to return.
queryYesNatural-language question or search text.
sinceNoRFC 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 (今天/今日/昨天/昨日/前天/上周/8月1日/8月10日到9月1日/最近...). 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.
untilNoRFC 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 (e.g., 昨天 end of day, 截至8月10日, 8月10日到9月1日). 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.
query_modeNoOptional 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_orderNoSort order for returned memories: 'desc' (newest first) or 'asc' (oldest first). Trigger: Pass 'desc' when the user asks for 'latest', 'recent', '从新到旧', or timeline recency, or 'asc' for chronological order. 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.
hypothetical_answerNoInput value for the Search Memory tool.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed5 schema fields changed
    • addedInput schema / properties / hypothetical_answer
      Added value: +{
+  "default": "",
+  "description": "Input value for the Search Memory tool.",
+  "title": "Hypothetical Answer",
+  "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 / 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 (今天/今日/昨天/昨日/前天/上周/8月1日/8月10日到9月1日/最近...). 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 / 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', '从新到旧', or timeline recency, or 'asc' for chronological order. 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 (e.g., 昨天 end of day, 截至8月10日, 8月10日到9月1日). 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"
+}
  2. Added
  3. Removed
  4. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safe read-only nature is covered. The description adds meaningful behavioral context beyond annotations by disclosing strong-match semantics and the fact that weak matches must not be surfaced as answers. This helps an agent predict strictness of retrieval behavior.

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 three concise sentences with no filler. The primary purpose and matching semantics are front-loaded, followed by sibling routing and a deletion pointer. Every sentence earns its place and directly supports correct tool selection and invocation.

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 seven-parameter complexity, the rich parameter descriptions in the schema, and the presence of an output schema, the description covers the essential selection and behavioral context. It identifies the core semantic distinction, names alternatives, and flags sibling tools. A small gap: it does not summarize the time-window or query-mode behaviors, but those are thoroughly explained in the schema parameter descriptions.

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%, so the schema itself fully documents all seven parameters, including triggers and model responsibilities for since, until, query_mode, and time_order. The description does not add parameter-level meaning beyond the schema, but it does not need to because the schema already carries that burden.

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 states a specific verb and resource ('Search XMemo memories') and clarifies the core semantic: strong-match, targeted lookup where weak matches must not be returned. It also names recall, recall_context, and forget as distinct sibling tools, so the agent can immediately tell this tool apart from alternatives.

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 says when to use this tool: targeted lookup requiring strong matches. It also gives exact alternatives: use recall for forgiving best-effort retrieval, recall_context for a bounded multi-memory context pack, and forget for deletion. This gives clear routing guidance with no need for inference.

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

All XMemo toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0
Disambiguation3/5

Multiple memory-retrieval tools (recall, search_memory, recall_context, read_memory, memory_overview) have overlapping purposes; detailed descriptions help but an agent could easily pick the wrong one. Similarly, ledger/open_ledger and todo/open_todo_board split text vs UI interaction, and forget overlaps with todo delete_all and ledger deletion.

Naming Consistency3/5

Most tools follow a verb_noun snake_case pattern (read_memory, update_memory, search_memory, open_ledger). However, several tools use bare nouns or verbs (forget, ledger, project, todo, recall, remember) and memory_overview is noun_noun, creating inconsistent conventions.

Tool Count3/5

19 tools is on the heavy side for the apparent scope, and the surface includes several pairs that duplicate the same domain in text vs UI form (ledger/open_ledger, todo/open_todo_board). Still, the count is defensible given the combined memory, project, TODO, and ledger coverage.

Completeness4/5

Memory has full lifecycle coverage (remember, read, search/recall, update, forget, restore), and TODO and Ledger workflows are largely complete. Minor gaps exist—no explicit project deletion and no pure text list-projects tool—but core workflows do not dead-end.

Resources