Skip to main content
Glama

mcp-notion__notion-get-version-changes

Read-onlyIdempotent

List what changed in a Notion page or database between two times, who changed it, and whether they used AI, an agent, or an MCP client. Each block, property, row, data source, or view that changed is listed once, with how it looked at the start and at the end of the time range. The range defaults to the last 24 hours. Filter by authors or sources to list only the records those people, agents, or kinds of edits touched; before and after still include everyone's edits, so use a shorter range to isolate one author. To read the whole page at a time, use view_version. Comments are not listed. Changes inside a page's inline databases are not listed either; pass an inline database's url to read them. Times are in UTC; convert them to the user's time zone before you show them. Requires edit access to the page. 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": {
      "page": "<page>"
    },
    "name": "mcp-notion__notion-get-version-changes"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageYesThe page or database to read: a page URL, database URL, data source (collection://) URL, or ID.
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.
authorsNoOnly return records that these people or agents changed: user:// URLs or agent URLs. Each record's before and after still include everyone's edits in the range, and contributors lists everyone who edited it.
site_idNoSite to run this tool on: ded71e55-0da4-4a52-8f14-1224fa9979b9 (https://mcp.notion.com/mcp)
sourcesNoOnly return records changed through these, such as ["notion_ai", "custom_agent", "mcp"] for changes made by AI. Each record's before and after still include every edit in the range, and contributors lists everyone who edited it.
end_timeNoEnd of the time range, included, as an ISO 8601 time with a time zone, such as "2026-10-10T18:05:02Z". Must be after start_time. Leave it out unless the user names a time; it defaults to now.
start_timeNoStart of the time range, not included, as an ISO 8601 time with a time zone, such as "2026-10-10T18:05:02Z". Leave it out unless the user names a time; it defaults to 24 hours before end_time.
instructions_versionNoNotion setup instructions version, such as 0.0.2. Omit if unknown.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description confirms it runs straight away ('its server marks it read-only'). It adds real behavioral context beyond that: requires edit access, times are UTC and must be converted for display, and before/after snapshots include everyone's edits even when filtering. It doesn't cover volume or pagination behavior for very large change sets.

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?

Dense but front-loaded: the core behavior comes first, then filtering caveats, then exclusions and operational notes (UTC, edit access). The authors and sources explanation is stated twice in near-identical form, which is the main redundancy, but nothing else is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, so the description must convey the return shape, and it does: each changed block, property, row, data source, or view is listed once with its start and end appearance. Combined with defaults, access requirements, time-zone handling, and exclusions, an agent has everything needed to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds genuine semantics the schema only hints at: the range defaults to the last 24 hours, and authors/sources filtering narrows which records are returned while before/after and contributors still reflect everyone's edits. That subtlety is not obvious from the parameter descriptions alone.

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?

A specific verb and resource: 'List what changed in a Notion page or database between two times,' plus the extra dimensions returned (who changed it, whether via AI/agent/MCP client). It explicitly distinguishes itself from view_version, so an agent can pick between them without opening a schema.

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?

Gives explicit routing: use view_version to read the whole page at a time; pass an inline database's url to read its changes; use a shorter range to isolate one author. It also states exclusions upfront (comments and inside-page inline databases are not listed), which is exactly the when-not guidance an agent needs.

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