Skip to main content
Glama
Sign In
Rememb

Rememb

by LuizEduPP
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

rememb_search

Search memory entries by keyword or short phrase to find relevant agent memories with optional tag and section filters. Returns IDs, scores, tags, dates, and excerpts for follow-up retrieval.

Instructions

Keyword and token search over memory entries. Safe, read-only. Returns id, score, tags, date, and a short excerpt. Use rememb_get for full body.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "rememb_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagNoOptional exact tag filter applied before keyword search
queryYesSearch query - keywords or short phrases
storeNoMemory store id. 'global' is the ~/.rememb store. Other ids are project stores passed via repeated --project MCP args.global
top_kNoMaximum number of results
sectionNoOptional section filter: project, actions, systems, requests, user, context
max_charsNoExcerpt length per entry. Default 160. 0 returns the full body.
include_deletedNoInclude soft-deleted entries in the search corpus and results

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv0.4.20
    • addedInput schema / properties / include_deleted
      Added value: +{
+  "default": false,
+  "description": "Include soft-deleted entries in the search corpus and results",
+  "type": "boolean"
+}
    • changedInput schema / properties / max_chars / description
      Previous value: -"Maximum characters of content to include per entry"New value: +"Excerpt length per entry. Default 160. 0 returns the full body."
    • changedInput schema / properties / query / description
      Previous value: -"Search query - natural language or keywords"New value: +"Search query - keywords or short phrases"
    • addedInput schema / properties / store
      Added value: +{
+  "default": "global",
+  "description": "Memory store id. 'global' is the ~/.rememb store. Other ids are project stores passed via repeated --project MCP args.",
+  "enum": [
+    "global"
+  ],
+  "type": "string"
+}
    • removedInput schema / properties / summary_only
      Removed value: -{
-  "default": true,
-  "description": "Render a compact one-line summary per entry",
-  "type": "boolean"
-}
    • changedInput schema / properties / tag / description
      Previous value: -"Optional exact tag filter applied before semantic search"New value: +"Optional exact tag filter applied before keyword search"
  2. Changed4 schema fields changedv0.4.11
    • addedInput schema / properties / max_chars
      Added value: +{
+  "description": "Maximum characters of content to include per entry",
+  "type": "integer"
+}
    • addedInput schema / properties / section
      Added value: +{
+  "description": "Optional section filter: project, actions, systems, requests, user, context",
+  "enum": [
+    "project",
+    "actions",
+    "systems",
+    "requests",
+    "user",
+    "context"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / summary_only
      Added value: +{
+  "default": true,
+  "description": "Render a compact one-line summary per entry",
+  "type": "boolean"
+}
    • addedInput schema / properties / tag
      Added value: +{
+  "description": "Optional exact tag filter applied before semantic search",
+  "type": "string"
+}
  3. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

No annotations are provided, so the description carries the burden and does so partly: it declares 'Safe, read-only' and enumerates the returned fields (id, score, tags, date, excerpt). It does not mention result ordering, soft-deleted entry behavior, or the top_k default, leaving some behavioral detail to the schema.

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?

Three short sentences, front-loaded with purpose and safety, then the return contract, then the alternative. Nothing wasted.

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?

With no output schema, the description usefully enumerates return fields, and it compensates for missing annotations by declaring read-only safety. Still silent on result ordering and pagination, which matters for a search tool with a top_k parameter.

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 every parameter is already documented in the schema; the description only glancingly implies excerpt sizing ('short excerpt'). No syntax, tokenization, or multi-word query semantics are added beyond the 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?

States a specific verb and resource ('Keyword and token search over memory entries') and distinguishes itself from the sibling rememb_get by noting the latter returns full bodies. An agent can pick this tool apart from rememb_recent or rememb_list_tags without opening the schema.

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 routes to rememb_get when the full body is needed, which is a real alternative. However it gives no guidance on when to prefer rememb_recent, rememb_list_tags, or section vs tag filtering, so coverage is partial.

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

Deploy Server

Other Tools