Skip to main content
Glama

get_workout_samples

Retrieve time-series sample data for a specific workout, including heart rate, speed, altitude, power, cadence, and GPS coordinates, sampled at the device's recording interval.

Instructions

Returns the time-series sample stream for one workout. Each sample: timestamp (ms), heartRate (bpm), speed (m/s), altitude (m), power (W), cadence, latitude, longitude. Sampled at the device's recording interval (typically 1 s). Long workouts (>2 h) may return thousands of records — use get_workout_fit with full=false for a compact summary instead. Throws SuuntoNotFoundError if the key is invalid. Read-only.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
workoutKeyYesOpaque server-assigned string returned by list_workouts. Not guessable or constructable — always discover via list_workouts first. Passing an invalid key throws SuuntoNotFoundError.

Implementation Reference

  • The core API method that fetches workout sample time-series data from Suunto's cloud API endpoint /v2/workout/samples/{workoutKey}. It calls this.json<any>() which performs an authenticated HTTP GET with retry logic and returns parsed JSON.
    getWorkoutSamples(workoutKey: string) {
      return this.json<any>(`/v2/workout/samples/${encodeURIComponent(workoutKey)}`);
    }
  • MCP tool definition for 'get_workout_samples' including the description and inputSchema. Declares the tool name, description of the time-series sample stream (HR, speed, altitude, power, etc.), and the required 'workoutKey' string parameter.
    {
      name: "get_workout_samples",
      description:
        "Returns the time-series sample stream for one workout. Each sample: timestamp (ms), heartRate (bpm), speed (m/s), altitude (m), power (W), cadence, latitude, longitude. Sampled at the device's recording interval (typically 1 s). Long workouts (>2 h) may return thousands of records — use get_workout_fit with full=false for a compact summary instead. Throws SuuntoNotFoundError if the key is invalid. Read-only.",
      inputSchema: {
        type: "object",
        properties: {
          workoutKey: {
            type: "string",
            minLength: 1,
            description: "Opaque server-assigned string returned by list_workouts. Not guessable or constructable — always discover via list_workouts first. Passing an invalid key throws SuuntoNotFoundError.",
          },
        },
        required: ["workoutKey"],
      },
    },
  • src/index.ts:329-332 (registration)
    The MCP CallToolRequestSchema handler case that dispatches 'get_workout_samples' by calling suunto.getWorkoutSamples(a.workoutKey) and serializing the result as JSON text.
    case "get_workout_samples": {
      const data = await suunto.getWorkoutSamples(a.workoutKey);
      return text(JSON.stringify(data));
    }
  • CLI handler for the 'get-workout-samples' command. Extracts the workoutKey from positional args, calls suunto.getWorkoutSamples(key), and outputs the result as JSON.
    case "get-workout-samples": {
      const key = rest[0] ?? die("Usage: get-workout-samples <workoutKey>");
      out(await suunto.getWorkoutSamples(key));
      break;
    }
Behavior4/5

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

Describes read-only nature (reads samples), typical sampling interval (1s), and the potential for large responses. With no annotations, it covers safety and performance implications well. However, it lacks explicit mention of side effects, rate limiting, or pagination behavior, though these are implied by the data volume warning.

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?

Single paragraph with front-loaded purpose, followed by field list, sampling detail, and alternative tool hint. Every sentence adds value with no redundancy or 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 no output schema, the description fully documents return fields and units. It handles the single parameter's constraints and warns about large data, making it actionable for the agent.

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?

Schema coverage is 100%, but the description adds meaningful context: workoutKey is opaque, server-assigned, must be discovered via list_workouts, and invalid keys throw SuuntoNotFoundError. This goes beyond the schema's description.

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?

The description clearly states it returns time-series sample streams for a single workout, listing all fields (timestamp, heartRate, speed, altitude, power, cadence, latitude, longitude). It distinguishes itself from the sibling get_workout_fit by noting that get_workout_fit provides a compact summary for long workouts.

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 tells when to use (to get sample stream for one workout) and when not to (long workouts >2h may return thousands of records, use get_workout_fit instead). Also warns that invalid workoutKey throws SuuntoNotFoundError, guiding the agent to validate keys beforehand.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/googlarz/suunto-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server