Intervals.icu MCP Server

Add events to the calendar

create_events

Add planned workouts, races, notes, or holidays/sickness to the athlete calendar, up to 50 events per call. Workouts sync to the athlete's watch when device integration is enabled.

Instructions

Add planned workouts, races, notes or holidays/sickness to the athlete calendar (up to 50 per call). Planned workouts sync to the athlete's watch when their device integration is enabled. Show the plan to the user and get agreement before calling. An entry with the same date, category and name as an existing one is skipped unless allow_duplicates is true. Check workout_check in the result and fix any warnings with update_event.

Workout text syntax (Intervals.icu): one step per line starting with "- ", e.g. "- 10m Z2 Pace", "- 1.5km 7:00/km Pace", "- 90s 85% Pace", "- 10m Ramp 60-80% HR", "- 5m Z2 HR". Durations: 30s, 90s, 1m30, 10m, 1h. Distances: 400mtr (meters!), 1.5km, 2mi — "400m" means 400 MINUTES. Repeats: a line ending in "Nx" (e.g. "Main set 4x") followed by its steps, then a blank line. Section lines like "Warmup"/"Cooldown" are labels. Text before the duration labels a step ("- Strides 20s Z5 Pace"). Power (rides): "75%" (of FTP), "200w", "150-180w", "Z2". Bpm ranges like "140-150bpm" are NOT supported; use HR zones or % HR.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`events`	Yes
`allow_duplicates`	No	Create even if an identical entry exists.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`created`	Yes
`skipped`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.0.0Sep 26, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Beyond the annotations, the description discloses key behavior: duplicate entries with the same date, category and name are skipped unless allow_duplicates is true, planned workouts sync to the watch, and the result exposes workout_check. This is meaningful behavioral context that annotations alone would not convey.

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?

The description is long but every part earns its place: the first paragraph covers core behavior and workflow, and the second paragraph is a dense but structured syntax reference with examples. It is front-loaded and contains 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?

Given the tool's complexity, an output schema, and the annotations, the description is highly complete: it covers entry types, limits, duplicate handling, synchronization, user agreement, post-call warning handling, and the full syntax needed to build workout descriptions. Nothing essential for correct invocation seems missing.

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

Parameters5/5

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

The description adds substantial meaning beyond the schema, especially for the workout-syntax parameter: it explains step format, durations, distances, repeats, labels, power, and unsupported bpm ranges. It also clarifies allow_duplicates behavior with concrete conditions. This more than compensates for the 50% schema description coverage.

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?

Description uses a specific verb ('Add') and resource ('athlete calendar'), and enumerates the accepted entry types: workouts, races, notes, holidays/sickness. The scope is further clarified by the 50-per-call limit and the watch-sync note, which helps distinguish this from library-oriented siblings like create_workouts.

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 gives clear preconditions — 'Show the plan to the user and get agreement before calling' — and a follow-up action: check workout_check and fix warnings with update_event. It does not explicitly name alternatives or conditions when NOT to use this tool, so it stops short of a full 5.

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