intervals-icu-mcp

Overview Schema Source Related Servers Discussions Admin

Icu Update Workout

icu_update_workout

Idempotent

Edit fields on an existing library workout by sending only the values you want to change; use it to rename, retag, recolor, move, or update workout steps without creating a new record.

Instructions

Change fields on an EXISTING library workout — only the fields you pass are sent.

To save a new workout use icu_create_workout. This edits the library workout only; calendar events are separate records changed with icu_update_event.

Input Schema

Name	Required	Description
`day`	No	PLAN folders only: updated day offset from plan start
`name`	No	Updated workout name
`tags`	No	Replacement tag list
`color`	No	Updated color (hex string)
`indoor`	No	Mark as an indoor workout
`target`	No	Updated device target type: AUTO, POWER, HR, or PACE
`folder_id`	No	Move the workout to this folder or plan
`athlete_id`	No	Athlete ID (for coaches managing multiple athletes)
`workout_id`	Yes	Library workout ID (from icu_get_workouts_in_folder)
`description`	No	Updated workout steps. For WORKOUT events the server parses this into structured, device-syncable steps with zones and a training load. Use Intervals.icu workout syntax: one step per line as '- <duration> <target>' (duration FIRST), grouped under Warmup / Main / Cooldown headers. Targets: bike '- 5m 85%', '- 5m Z4', or absolute '- 5m 210w'; HR '- 10m 70-80% HR' or '- 10m 145bpm'; run/swim pace '- 5m Z2 Pace', absolute only with a trailing 'pace' word: '- 5m 4:45/km pace', '- 200mtr 1:45/100m pace' (bare '5:00/km' or '1:45/100m' silently drops); threshold is relative — run '- 25m 100% pace', swim CSS '- 200mtr 100% pace' — the words 'threshold'/'CSS'/'5K pace' are NOT parsed as targets. Add cadence to any step: '- 3m Z2 90rpm'. No target: '- 20m free'. Repeats: put 'Nx' after a section name with steps flat beneath, and leave a blank line before and after the repeat block (without it the repeat silently runs only once) — e.g. 'Main 5x' then '- 3m 110%' / '- 3m 50%'. Ramps: '- 10m ramp 50-70%'. Rest: append 'Ns rest' to a step ('- 200mtr Z2 20s rest') or use a separate '- 20s intensity=rest' step (only intensity=rest exports as a device rest step) — never a bare '- 20s' step (that becomes work, not rest). Durations: 'm'=minutes, 's'=seconds; distance steps use 'mtr'=meters / 'km' / 'yrd' (e.g. swim '- 400mtr Z2 Pace'). Do NOT write '[repeat 5x ...]', nested bullets, or 'Z5 3m' (target before duration). Runs need a pace or HR target — a bare 'Z2' gives no load. Full reference: intervals-icu://workout-syntax resource.
`workout_type`	No	Updated activity discipline: Ride, Run, Swim, Walk, Hike, WeightTraining, Workout, VirtualRide, VirtualRun, Other (full discipline list: intervals-icu://event-categories resource)
`training_load`	No	Updated training load
`distance_meters`	No	Updated distance in meters
`duration_seconds`	No	Updated duration in seconds

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Addedv5.1.0Sep 17, 2026

TDQS

A4.7/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, openWorldHint=true, so the safety profile is covered. The description adds genuinely useful behavior beyond them: partial-update semantics ('only the fields you pass are sent', i.e. omitted fields are left untouched) and the library-vs-calendar record boundary. It stops short of noting any side effects on existing derived data (e.g. re-parsing steps and recomputing training load), which the schema hints at but the description does not surface.

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 short sentences, front-loaded with the core action and its partial-update contract, then the disambiguation. No repetition of schema details and 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?

For a 14-parameter mutation the description covers exactly what the structured data does not: partial-update semantics and sibling routing. Per-field semantics and the workout-syntax reference live in a fully-covered schema, an output schema exists for return values, and annotations cover the safety profile, so nothing an agent needs to call this correctly is missing.

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 description coverage is 100%, so the baseline is 3 and the schema carries all per-field meaning, including the extensive workout-syntax grammar for `description`. The description adds one cross-cutting semantic that applies to all 13 optional params — that unspecified fields are not sent — which is precisely the guidance an agent needs to use the nullable-with-default pattern correctly.

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?

States a specific verb ('Change fields') plus resource ('EXISTING library workout') and immediately scopes it to partial updates ('only the fields you pass are sent'). It explicitly names the two sibling tools it must not be confused with (icu_create_workout, icu_update_event), so an agent can route correctly without opening any 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 when-to-use (edit an existing library workout), when-not-to-use with the exact alternative for each case ('To save a new workout use icu_create_workout'), and a sharp exclusion ('calendar events are separate records changed with icu_update_event'). Nothing about tool selection is left to inference.

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

Deploy Server