intervals-icu-mcp

Overview Schema Source Related Servers Discussions Admin

Icu Update Wellness

icu_update_wellness

Idempotent

Create or update wellness data for one date, sending only the fields you provide and optionally locking the record to prevent device sync overwrites.

Instructions

Upsert wellness data for ONE specific date — creates the record if missing, otherwise updates the fields you pass.

Only provided fields are sent. Subjective scales (fatigue, soreness, stress, mood, motivation, injury) are 1-5. Pass locked=True to stop device sync from overwriting manual entries. Writes to the authenticated athlete unless athlete_id names a managed athlete.

Input Schema

Name	Required	Description
`hrv`	No	HRV (rMSSD) value
`date`	Yes	Date in YYYY-MM-DD format
`mood`	No	Mood level (1-5 scale)
`spo2`	No	Blood oxygen saturation percentage (SpO2)
`injury`	No	Injury severity (1-5 scale: 1=none, 5=severe)
`locked`	No	Lock record to prevent device sync from overwriting manual entries
`stress`	No	Stress level (1-5 scale)
`vo2max`	No	VO2max (ml/kg/min) — lab result or device estimate
`weight`	No	Weight in kg
`abdomen`	No	Abdominal circumference in cm
`fatigue`	No	Fatigue level (1-5 scale)
`lactate`	No	Blood lactate in mmol/L — lab result
`protein`	No	Protein consumed (grams)
`body_fat`	No	Body fat percentage
`comments`	No	Comments or notes
`soreness`	No	Soreness level (1-5 scale)
`systolic`	No	Systolic blood pressure in mmHg
`diastolic`	No	Diastolic blood pressure in mmHg
`fat_total`	No	Total fat consumed (grams)
`hydration`	No	Subjective hydration rating (1-4: 1=well hydrated, 4=very dehydrated)
`readiness`	No	Readiness score (0-100)
`athlete_id`	No	Athlete ID (for coaches managing multiple athletes)
`motivation`	No	Motivation level (1-5 scale)
`resting_hr`	No	Resting heart rate in bpm
`sleep_secs`	No	Sleep duration in seconds
`respiration`	No	Respiration rate in breaths per minute
`blood_glucose`	No	Blood glucose in mmol/L
`carbohydrates`	No	Carbohydrates consumed (grams)
`sleep_quality`	No	Sleep quality (1-5 scale)
`menstrual_phase`	No	Menstrual phase (e.g. FOLLICULAR, OVULATING, LUTEAL, MENSTRUAL)
`hydration_liters`	No	Hydration volume (liters)
`calories_consumed`	No	Calories consumed (kcal)

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv5.0.1Sep 11, 2026

addedInput schema / properties / athlete_id

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Athlete ID (for coaches managing multiple athletes)"
+}

addedInput schema / properties / hydration

Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Subjective hydration rating (1-4: 1=well hydrated, 4=very dehydrated)"
+}

First observedv0.1.0May 19, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare idempotentHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered; the description adds real substance on top — upsert branch behavior, partial-send semantics, the lock/sync-overwrite interaction, and the authenticated-vs-managed-athlete write target. The remaining gap is that with every field nullable and defaulting to null, it never says whether passing an explicit null clears a stored value or is simply ignored, which matters for a mutation tool.

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?

Four tight sentences with the most important fact (upsert on one date) front-loaded and no filler. The scale enumeration partly restates schema descriptions, which is the only real redundancy.

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?

An output schema exists, so return values need no explanation, and the 32-parameter surface is fully described in the schema itself. The description covers the behaviors an agent can't get from structured fields — upsert branching, partial sends, lock behavior, write target — leaving only the null-vs-omit question and any permission prerequisites unaddressed.

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% across 32 parameters, so the per-field semantics are already documented and the baseline is 3. The description adds one genuinely schema-absent rule — that omitted fields are not sent, making this a partial update rather than a full replace — plus a consolidated statement of the 1-5 subjective scales and the athlete_id targeting rule.

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 and resource (upsert wellness data), pins the scope to ONE date, and explains the create-or-update branch in the same sentence. This clearly separates it from the read-side siblings icu_get_wellness_data and icu_get_wellness_for_date without requiring the agent to open 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 Guidelines4/5

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

Gives concrete usage conditions: partial updates are allowed ('Only provided fields are sent'), locked=True suppresses device-sync overwrites, and the write target is the authenticated athlete unless athlete_id is supplied. It does not explicitly route to the read tools for retrieval-only cases, so an agent must infer that from the verb.

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

Deploy Server