Skip to main content
Glama

mcp-notion__notion-memory-search

Read-onlyIdempotent

Search memories saved in the user's Notion workspace: context, preferences, corrections, and decisions. Returns the best matches, not every memory. To list, count, or filter memories, fetch id "memory" and run query-data-sources on its data source. Read notion://docs/memory once before using Notion memory in a conversation. Reading never authorizes a write. If the user says "remember this" without choosing Notion, ask where to save it. Through Royally: its server marks it read-only, so it runs straight away.

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": "mcp-notion__notion-memory-search"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum number of memories to return. Defaults to 10 and cannot exceed 50.
queryYesWords or a short phrase to find in personal memories.
skillNoFor tracking only: the name of the agent skill you are following for this task, such as notion-meeting-prep. Omit if you are not following a skill.
site_idNoSite to run this tool on: ded71e55-0da4-4a52-8f14-1224fa9979b9 (https://mcp.notion.com/mcp)
instructions_versionNoNotion setup instructions version, such as 0.0.2. Omit if unknown.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
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, and the description is consistent with that, adding the useful clarification that 'Reading never authorizes a write'. It also discloses ranking behavior (best matches, not exhaustive), which annotations cannot convey. The 'server marks it read-only, so it runs straight away' sentence largely restates the annotation rather than adding new behavior.

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?

The core purpose and the 'best matches' caveat are front-loaded in the first two sentences, before routing and prerequisite details. It is dense but organized; the 'Through Royally' sentence is the weakest, mostly restating the read-only annotation and adding client-specific noise.

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 five-parameter read tool with no output schema, the definition covers purpose, ranking semantics, prerequisites, routing to alternatives, and safety expectations. What it does not cover is the shape of returned matches (only 'best matches') and whether pagination or scoring is exposed, which is a modest gap given no output schema exists.

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 query, limit, skill, site_id and instructions_version are already documented in the schema. The description adds only the relevance-ranking implication of limit ('best matches, not every memory') and says nothing about the query format, the tracking-only nature of skill, or the fixed site_id. Baseline 3 applies when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource ('Search memories saved in the user's Notion workspace') and enumerates the memory kinds (context, preferences, corrections, decisions), which separates it from a general workspace search. It also states the retrieval semantics ('Returns the best matches, not every memory'). It stops short of contrasting itself by name with mcp-notion__notion-search, so a 4 rather than a 5.

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?

It gives explicit when-to-use (searching memories), explicit when-not with a concrete alternative path for list/count/filter ('fetch id "memory" and run query-data-sources on its data source'), and a prerequisite ('Read notion://docs/memory once before using Notion memory'). It also specifies an ambiguity-resolution rule: if the user says 'remember this' without choosing Notion, ask where to save it.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources