Smara Memory MCP Server

Search Memories

search_memories

Search stored memories using natural language queries, balancing semantic relevance with memory freshness and importance. Returns both private and team memories when configured.

Instructions

Semantic search across stored memories for a user. Ranked by Temporal Memory Scoring — balances semantic relevance with memory freshness and importance. When a team is configured, returns both private and team memories by default.

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": {
      "user_id": "<user_id>",
      "q": "<q>"
    },
    "name": "search_memories"
  }
}

Input Schema

Name	Required	Description
`user_id`	Yes	User to search memories for
`q`	Yes	Natural language search query
`limit`	No	Max results to return
`namespace`	No	Memory namespace (default: from env or 'default')
`team_id`	No	Team ID to include team memories from. Defaults to SMARA_TEAM_ID env var.
`include_team`	No	Include team memories in results. Defaults to true when a team is configured.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv2.2.0Apr 21, 2026

TDQS

A4.2/5.0

Behavior4/5

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

With no annotations provided, the description carries full burden and adds valuable behavioral context: it explains the ranking algorithm ('balances semantic relevance with memory freshness and importance'), specifies default team memory inclusion behavior, and mentions configuration dependencies ('when a team is configured'). It doesn't cover error conditions, rate limits, or authentication needs, but provides substantial operational insight beyond basic functionality.

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 concise sentences with zero waste: first states core purpose, second explains ranking methodology, third clarifies team behavior. Each sentence adds distinct value, and the description is appropriately front-loaded with the main functionality.

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?

For a search tool with 6 parameters, 100% schema coverage, and no output schema, the description provides good context about ranking methodology and team behavior. It doesn't describe return format or result structure, which would be helpful given no output schema, but covers the essential operational context well for a read-only search operation.

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 already documents all 6 parameters thoroughly. The description adds minimal parameter-specific information beyond what's in the schema - it mentions team configuration defaults but doesn't elaborate on parameter interactions or search semantics. Baseline 3 is appropriate when schema does the heavy lifting.

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 performs 'semantic search across stored memories for a user' with specific ranking methodology ('Temporal Memory Scoring'), distinguishing it from siblings like list_memories (which likely lists without search) or get_user_context (which might retrieve context without search). It specifies both the action (search) and resource (memories) precisely.

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?

The description provides clear context for when to use this tool: for semantic search of memories. It mentions default behavior for teams ('returns both private and team memories by default'), which helps differentiate from list_memories (which might not include team memories). However, it doesn't explicitly state when NOT to use it or name specific alternatives among siblings.

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

Deploy Server