Skip to main content
Glama
samitugal
by samitugal

get-activity-streams

Retrieve time-series data streams for a Strava activity, including heart rate, power, GPS, pace, and elevation. Supports pagination, configurable resolution, and downsampling for large datasets.

Instructions

Returns time-series data streams (heart rate, power, GPS, pace, elevation) for an activity at configurable resolution, with pagination and intelligent downsampling for large datasets.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNoOptional page number for paginated results. Use with points_per_page to retrieve specific data ranges. Example: page=2 with points_per_page=100 gets points 101-200.
typesNoArray of stream types to fetch. Available types: - time: Time in seconds from start - distance: Distance in meters from start - latlng: Array of [latitude, longitude] pairs - altitude: Elevation in meters - velocity_smooth: Smoothed speed in meters/second - heartrate: Heart rate in beats per minute - cadence: Cadence in revolutions per minute - watts: Power output in watts - temp: Temperature in Celsius - moving: Boolean indicating if moving - grade_smooth: Road grade as percentage
formatNoOutput format: - compact: Raw arrays, minified JSON (~70-80% smaller, LLM-friendly) - verbose: Human-readable objects with formatted values (backward compatible)compact
activityIdYesThe Strava activity identifier to fetch streams for. This can be obtained from activity URLs or the get-activities tool.
max_pointsNoMaximum number of data points to return. If activity exceeds this, data will be intelligently downsampled while preserving peaks and valleys. Useful for very large activities.
resolutionNoData resolution. Affects number of data points returned: - low: ~100 points (recommended for LLM analysis) - medium: ~1000 points - high: ~10000 points (warning: very large payload, may cause slowness) Defaults to "low" when omitted. Pass explicitly if you need more data.
series_typeNoOptional base series type for the streams: - time: Data points are indexed by time (seconds from start) - distance: Data points are indexed by distance (meters from start) Useful for comparing different activities or analyzing specific segments.distance
summary_onlyNoIf true, returns only metadata and statistics (min/max/avg) without raw stream data. Much faster and smaller response. Ideal for quick activity overviews or when raw data is not needed.
points_per_pageNoOptional number of data points per page. Special values: - Positive number: Returns that many points per page - -1: Returns ALL data points split into multiple messages (~1000 points each) Use -1 when you need the complete activity data for analysis.
Behavior4/5

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

No annotations are provided, so the description carries full responsibility for disclosing behavior. It explains return type (time-series streams), key behavioral traits like configurable resolution, pagination, and intelligent downsampling for large datasets. This is substantive beyond the schema. It does not mention error conditions or auth requirements, but the core behavior is well covered.

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 a single sentence that efficiently conveys the core purpose and key features without waste. It lists relevant stream types and mentions resolution, pagination, and downsampling in a compact, readable format.

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?

Given that there is no output schema and 9 parameters, the description helps by summarizing the key capabilities. It does not detail return shapes or edge cases, but the schema covers parameter semantics thoroughly, and the description orients the agent to the tool's main value. It is complete enough for an informed agent to select and invoke it correctly.

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

Parameters3/5

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

The schema description coverage is 100%, with detailed parameter descriptions for types, resolution, series_type, summary_only, points_per_page, etc. The tool description adds a high-level summary of resolution and pagination but does not provide additional meaning beyond what the schema already offers. Baseline 3 is appropriate because the schema does the heavy lifting.

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 what the tool does: returns time-series data streams (heart rate, power, GPS, pace, elevation) for an activity. It specifies the resource (activity streams) and key features (configurable resolution, pagination, downsampling), which distinguishes it from sibling tools like get-activity-details or get-activity-laps.

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 implies the tool is for retrieving detailed time-series data for a specific activity, which is distinct from the other activity-related tools. It provides clear context (configurable resolution, pagination, downsampling) but does not explicitly mention alternatives or exclusions. Since siblings like get-activity-details are for metadata, the purpose is clear enough without explicit when-not guidance.

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/samitugal/strava-mcp'

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