Fitbit MCP

Fitbit Heart Series

fitbit_heart_series

Read-onlyIdempotent

Retrieve a day's heart-rate time series with exact statistics and a downsampled series capped at 500 points, revealing HR trends across the day.

Instructions

Bounded heart-rate time-series for one civil day (agent-safe-series/v1). Exact stats on full-resolution samples plus a downsampled series capped at 500 points. Prefer fitbit_get_heart_day / daily summary first; use this when you need the shape of HR over the day. Shared contract with garmin_activity_series / strava_activity_series / Kindred workout_series. Not medical advice.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`date`	No	Date as yyyy-MM-dd or today. ISO date-times are reduced to the written calendar day.	today
`end_time`	No	Optional HH:mm window end (local Fitbit day).
`max_points`	No	Point budget. Server hard cap is 500.
`start_time`	No	Optional HH:mm window start (local Fitbit day).
`detail_level`	No	Upstream Fitbit sample density. Series tool still enforces max_points server-side. Prefer 1min; 1sec needs personal/intraday access.	1min
`response_format`	No		markdown
`reference_max_hr`	No	Reference max HR for zone math (reference_source=caller_provided).
`resolution_seconds`	No	Requested bucket width. Raised automatically under max_points pressure.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`unit`	Yes
`notes`	Yes
`stats`	Yes
`method`	Yes
`metric`	Yes
`points`	Yes
`t_unit`	Yes
`start_time`	No
`activity_id`	Yes
`downsampled`	Yes
`data_quality`	Yes
`time_in_zone`	No
`source_points`	Yes
`returned_points`	Yes
`contract_version`	Yes
`resolution_seconds`	Yes
`requested_resolution_seconds`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv0.6.3Sep 4, 2026
- removedOutput schema / properties / activity_id / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "number"
-  }
-]
```
- addedOutput schema / properties / activity_id / type
```
Added value: +[
+  "string",
+  "number"
+]
```
- removedOutput schema / properties / time_in_zone / properties / zones / items / properties / max_bpm / anyOf
```
Removed value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / time_in_zone / properties / zones / items / properties / max_bpm / type
```
Added value: +[
+  "number",
+  "null"
+]
```
Addedv0.6.0Aug 7, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds meaningful behavioral context: the series is bounded, capped at 500 points, downsampled, and 'agent-safe-series/v1'. It also discloses 'Not medical advice'. No contradictions with annotations. The description enriches the safety profile with cap and downsampling details.

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 concise sentences with no filler. The main purpose is front-loaded, followed by usage guidance and the contract note. Every sentence earns its place; it is compact and scannable.

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 the complexity (8 parameters, output schema present), the description is complete enough. It explains the core behavior, usage preference, and a safety caveat. The output schema covers return structure, so the description doesn't need to detail it. The only minor gap is that it doesn't explicitly mention pagination or rate limits, but the cap is already stated.

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?

Schema description coverage is 88% (high), so the schema itself documents parameters well. The description does not add extra parameter semantics; it mentions 'capped at 500 points' which relates to max_points but not explicitly, and 'one civil day' which relates to the date parameter. Since the schema already carries the weight, a baseline 3 is appropriate.

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?

Clearly states the tool returns a bounded heart-rate time-series for one civil day, with explicit mention of exact stats and a downsampled series. It distinguishes itself from daily summaries by saying 'use this when you need the shape of HR over the day' and names the preferred alternative, so an agent can tell it apart from siblings without inspecting schemas.

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?

Provides explicit guidance: 'Prefer fitbit_get_heart_day / daily summary first; use this when you need the shape of HR over the day.' This directly tells the agent when to select this tool over alternatives. Also notes a shared contract with other series tools, implying a family pattern.

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