Skip to main content
Glama
Sign In
xichen-de

garmin-owl

by xichen-de
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

get_running_tolerance

Read-only

Retrieve Garmin running distance, impact load, tolerance, and feedback for 1–90 days ending on a chosen date to track running-specific load history and distinguish it from general training load.

Instructions

Get Garmin running distance, impact load, tolerance, and feedback for 1-90 days ending on end_date.

Use for running-specific load/tolerance history; use get_training_load for general training- load metrics. Missing device metrics are not estimated.

Requires saved local Garmin authentication (garmin-owl-auth). Reads Garmin and may update the local cache; never changes your Garmin account. Garmin failures are not retried automatically.

Input Schema

NameRequiredDescriptionDefault
daysNoNumber of days from 1 to 90, ending on end_date inclusive; defaults to 28.
end_dateNoInclusive end date, YYYY-MM-DD; omit or pass null for today in the server's local timezone.

Output Schema

NameRequiredDescriptionDefault
noteNoGarmin-provided running distance, biomechanical impact load, and tolerance only; no injury-risk prediction or recommendation.
pointsNo
end_dateYes
start_dateYes
availabilityNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changedv0.3.1
    • addedInput schema / properties / days / description
      Added value: +"Number of days from 1 to 90, ending on end_date inclusive; defaults to 28."
    • addedInput schema / properties / days / maximum
      Added value: +90
    • addedInput schema / properties / days / minimum
      Added value: +1
    • changedInput schema / properties / end_date / anyOf
      Previous value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
    • addedInput schema / properties / end_date / description
      Added value: +"Inclusive end date, YYYY-MM-DD; omit or pass null for today in the server's local timezone."
    • addedOutput schema / $defs
      Added value: +{
+  "AvailabilityNotice": {
+    "properties": {
+      "field": {
+        "title": "Field",
+        "type": "string"
+      },
+      "message": {
+        "title": "Message",
+        "type": "string"
+      },
+      "status": {
+        "title": "Status",
+        "type": "string"
+      }
+    },
+    "required": [
+      "field",
+      "status",
+      "message"
+    ],
+    "title": "AvailabilityNotice",
+    "type": "object"
+  },
+  "RunningTolerancePoint": {
+    "properties": {
+      "acute_distance_m": {
+        "anyOf": [
+          {
+            "type": "number"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Acute Distance M"
+      },
+      "acute_impact_load": {
+        "anyOf": [
+          {
+            "type": "number"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Acute Impact Load"
+      },
+      "acute_tolerance": {
+        "anyOf": [
+          {
+            "type": "number"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Acute Tolerance"
+      },
+      "date": {
+        "title": "Date",
+        "type": "string"
+      },
+      "feedback": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Feedback"
+      }
+    },
+    "required": [
+      "date"
+    ],
+    "title": "RunningTolerancePoint",
+    "type": "object"
+  }
+}
    • removedOutput schema / additionalProperties
      Removed value: -true
    • addedOutput schema / properties
      Added value: +{
+  "availability": {
+    "items": {
+      "$ref": "#/$defs/AvailabilityNotice"
+    },
+    "title": "Availability",
+    "type": "array"
+  },
+  "end_date": {
+    "title": "End Date",
+    "type": "string"
+  },
+  "note": {
+    "default": "Garmin-provided running distance, biomechanical impact load, and tolerance only; no injury-risk prediction or recommendation.",
+    "title": "Note",
+    "type": "string"
+  },
+  "points": {
+    "items": {
+      "$ref": "#/$defs/RunningTolerancePoint"
+    },
+    "title": "Points",
+    "type": "array"
+  },
+  "start_date": {
+    "title": "Start Date",
+    "type": "string"
+  }
+}
    • addedOutput schema / required
      Added value: +[
+  "start_date",
+  "end_date"
+]
    • changedOutput schema / title
      Previous value: -"get_running_toleranceDictOutput"New value: +"RunningTolerance"
  2. Addedv0.2.0

TDQS

A4.7/5.0
Behavior5/5

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

Goes well past the readOnly/openWorld annotations: it discloses the garmin-owl-auth prerequisite, that the local cache may be written even though the Garmin account is never modified, and that Garmin failures are not retried. 'Missing device metrics are not estimated' is an unusual and valuable data-quality caveat that an agent would otherwise have to discover empirically.

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?

Four short sentences in a deliberate order: what it returns, when to use it versus the sibling, prerequisites/side effects, failure behavior. Each sentence carries a distinct fact with no 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?

For a two-optional-parameter read with an output schema, everything an agent needs to call it correctly is present: scope, alternative routing, auth requirement, cache side effect, and failure semantics. Return-value shape is rightly delegated to the output schema.

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 100%, so both parameters (days, end_date) are already fully documented with defaults and bounds in the schema. The description's restatement of the 1-90 range and inclusive end date adds no syntax or format detail beyond that, so the baseline of 3 applies.

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?

States a specific verb (Get) plus the exact resource set (Garmin running distance, impact load, tolerance, feedback) and the scope window (1-90 days ending on end_date). It also names the sibling get_training_load as the non-running counterpart, so the agent can separate the two without opening 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?

'Use for running-specific load/tolerance history; use get_training_load for general training-load metrics' gives an explicit when-to-use and a named alternative for the adjacent case. No exclusions are left to inference.

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

Deploy Server

Other Tools