TimeTree MCP Server

get_recent_activity

Read-only

Track recent calendar activity by returning who created, changed, or deleted events and memos, newest first, so you can review recent changes and identify actors.

Instructions

See who recently created, changed, or deleted events and memos in a calendar, newest first (created, title/date/label/note/location/reminder/URL/checklist updated, deleted), with member names. TimeTree keeps only the last few activities per event, so this is a recent feed, not full history. Use get_updated_events for the current content of changed events.

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": {
      "calendar_id": "<calendar_id>"
    },
    "name": "get_recent_activity"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Maximum number of events to return (1-100, default 20)
`since`	No	Only return activity after this Unix timestamp in milliseconds
`calendar_id`	Yes	The calendar ID from list_calendars (numeric string; numbers are also accepted)

Output Schema

Name	Required	Description	Default
`total`	Yes
`events`	Yes
`calendar_id`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.7.0Oct 22, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "calendar_id": {
+      "type": "string"
+    },
+    "events": {
+      "items": {
+        "properties": {
+          "activities": {
+            "items": {
+              "properties": {
+                "actions": {
+                  "items": {
+                    "type": "string"
+                  },
+                  "type": "array"
+                },
+                "at": {
+                  "type": "string"
+                },
+                "user_id": {
+                  "type": [
+                    "number",
+                    "null"
+                  ]
+                },
+                "user_name": {
+                  "type": [
+                    "string",
+                    "null"
+                  ]
+                }
+              },
+              "required": [
+                "actions",
+                "at"
+              ],
+              "type": "object"
+            },
+            "type": "array"
+          },
+          "all_day": {
+            "type": [
+              "boolean",
+              "null"
+            ]
+          },
+          "deleted": {
+            "type": "boolean"
+          },
+          "kind": {
+            "enum": [
+              "event",
+              "memo"
+            ],
+            "type": "string"
+          },
+          "start_at": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "title": {
+            "type": "string"
+          },
+          "uuid": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "uuid",
+          "title",
+          "kind",
+          "deleted",
+          "activities"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "total": {
+      "type": "number"
+    }
+  },
+  "required": [
+    "calendar_id",
+    "events",
+    "total"
+  ],
+  "type": "object"
+}

Addedv0.4.0Oct 3, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already cover read-only and open-world, so the description's added value is the retention caveat ('TimeTree keeps only the last few activities per event, so this is a recent feed, not full history') and the 'newest first' ordering — both real behavioral traits an agent cannot infer from structured fields. It stops short of noting rate limits or per-event truncation details, so not a 5.

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 tight sentences: purpose and scope first, retention caveat second, alternative-tool routing last. No repetition of schema or annotation content, no filler.

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?

With an output schema present, return shape needn't be explained, and the description still names the activity fields. Combined with the retention caveat and sibling routing, an agent has everything needed to select and call this correctly.

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 coverage is 100% and each of the three parameters (limit, since, calendar_id) is already documented there. The description adds no syntax, default, or format guidance beyond the ordering hint, so baseline 3 applies.

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?

Opens with a specific verb and resource ('See who recently created, changed, or deleted events and memos in a calendar') and then enumerates exactly which change types count. An agent can distinguish it from read/CRUD siblings like get_events and get_updated_events without consulting 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 Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly routes the agent: 'Use get_updated_events for the current content of changed events,' which is the one realistic confusion case. It also implicitly scopes usage to recent-feed questions rather than full-history queries.

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