Skip to main content
Glama

get_health_trends

Compute rolling averages, half-window deltas, and training volume for RHR, HRV, sleep, steps, and stress over N days to detect multi-week trends and early overtraining signals.

Instructions

Compute longitudinal rolling averages, first-half vs. second-half deltas, and training volume over N days.

Coaching Purpose: Detects multi-week physiological trends and early overtraining signals across Resting Heart Rate (RHR), overnight HRV, sleep duration, daily steps, daily stress, and total training volume (hours, distance, activity breakdown) over a configurable window (e.g., 7, 14, 28, 30, or 90 days).

Args: days: Number of days to aggregate (default 28). Clamped to a positive integer. end_date: End ISO date (YYYY-MM-DD) of the analysis window. Defaults to today. response_format: Output representation: "markdown", "json", or "hybrid" (default).

Returns: Formatted longitudinal trend report with biomarker averages, min/max, 1st-half vs. 2nd-half deltas, trend directions, training volume totals, and diagnostic coach flags.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_health_trends"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNo
end_dateNo
response_formatNohybrid

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does reasonably well: it discloses the input clamping behavior for days, the today-default for end_date, the diagnostic coach flags in the output, and the configurable window options. It stops short of noting data-sufficiency requirements or cost/latency for long windows like 90 days, which would matter for an aggregation call.

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?

A one-sentence summary is front-loaded, followed by clearly separated Purpose/Args/Returns blocks, so an agent can scan to the relevant section quickly. There is minor redundancy where defaults (28, hybrid) repeat the schema's own defaults, but nothing is padded or off-topic.

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?

For an aggregation tool with three optional parameters, the description covers inputs, computed outputs, and diagnostics adequately, and the presence of an output schema means return values needn't be fully restated. What remains thin is guidance on data requirements and how the result relates to the shorter-horizon sibling tools.

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 description coverage is 0%, so the description must compensate fully and it does: days is documented with its default and clamping rule, end_date with the exact YYYY-MM-DD format and its window-role, and response_format with all three enum meanings plus the default. This is more than the bare schema conveys, since the schema supplies no descriptions at all.

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?

The opening sentence names specific computations (rolling averages, first-half vs. second-half deltas, training volume over N days) and the second lists the exact biomarkers covered, so the agent knows precisely what the tool produces. It does not, however, contrast itself with overlapping siblings like get_sleep_and_recovery or get_training_status_and_load, leaving ambiguity about which tool to prefer for overlapping metrics.

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?

The 'Coaching Purpose' paragraph implies usage (detecting multi-week trends and early overtraining signals) which points toward when this tool is appropriate. But there is no explicit when-to-use/when-not, no stated prerequisites (e.g., minimum data history), and no routing to or away from the sibling tools that report the same biomarkers over shorter horizons.

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