Intervals.icu MCP Server

Get activity intervals

get_activity_intervals

Read-only

Retrieve the lap and interval breakdown for a training activity, returning a compact 24-field summary per lap by default or custom fields on request.

Instructions

Get the lap/interval breakdown for an activity. Each lap carries 84 fields, so a compact subset is returned by default; fields applies to the individual laps inside icu_intervals and icu_groups.

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": {
      "activity_id": "<activity_id>"
    },
    "name": "get_activity_intervals"
  }
}

Input Schema

Name	Required	Description	Default
`fields`	No	Fields to return. Defaults to a compact 24-field summary; the full record has ~84 fields, many of them null. Pass ["*"] for everything.
`activity_id`	Yes	The activity ID

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Oct 16, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds genuinely useful behavioral context beyond that: laps have 84 fields, a compact subset is returned by default, and the response is organized into icu_intervals and icu_groups. It stops short of noting pagination or other limits, but that gap is minor against the annotation coverage.

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?

Two sentences, zero padding. The purpose is front-loaded in the first sentence and the non-obvious nested-field scoping caveat follows immediately.

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?

With no output schema, the description carries the burden of describing returns; it names the top-level result keys (icu_intervals, icu_groups) and the default compact shape, which is enough for an agent to call it correctly. A note on what the default 24 fields actually contain would close the remaining gap.

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 baseline is 3. The description goes further by clarifying the scope of `fields`: it applies to the individual laps nested inside icu_intervals and icu_groups, not to top-level records. That is real meaning the schema's generic 'Fields to return' text does not convey.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Get the lap/interval breakdown for an activity.' This is clearly distinct from the plain get_activity sibling, though it never names that sibling or any other alternative explicitly. An agent can infer the distinction from the resource scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

Usage is only implied: you call this when you need lap/interval detail rather than an aggregate activity record. No when-to-use condition, no exclusions, and no pointer to get_activity or get_activity_streams for related data.

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