Skip to main content
Glama

garmin_delete

Destructive

Permanently delete selected Garmin Connect weigh-ins, blood pressure, workouts, food logs, or courses after previewing them; confirm to remove only previewed items, with no undo.

Instructions

Permanently delete from Garmin Connect: weigh_ins (all on the date, or the ids given), blood_pressure, workouts, scheduled_workouts (unschedule), custom_food, food_log, course. Without confirm it only previews. With confirm=true it deletes only what was previewed in the last 15 minutes. There is no undo.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "kind": "<kind>"
    },
    "name": "garmin_delete"
  }
}

Input Schema

NameRequiredDescriptionDefault
idsNoIds from the read tools (weigh-in id, workout id, scheduled_id, ...)
dateNoNeeded for weigh_ins, blood_pressure and food_log
kindYes
confirmNotrue only after the user agreed to the preview

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description adds genuinely new behavioral context on top: irreversibility ('There is no undo') and the temporal coupling of confirm to the last preview within 15 minutes. It also discloses deletion scope ('all on the date, or the ids given') and that scheduled_workouts means unschedule, not removal.

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?

Compact and front-loaded: the kind enumeration and preview/confirm contract come first, and every clause carries information. The telegraphic list style is efficient though slightly denser than ideal to scan.

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 a destructive, no-output-schema tool with four parameters, the definition covers the safety-critical facts an agent needs: scope, preview gate, time window, no undo. Minor gaps remain — no mention of error behavior when confirming without a preview, and no note on required account permissions.

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

Parameters4/5

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

Schema coverage is 75%, so ids, date and confirm are already partly documented. The description still adds meaning the schema does not: that weigh_ins can be deleted wholesale by date or selectively by ids, and that confirm only acts on the previously previewed set within a 15-minute window — a semantic constraint absent from the confirm field's own 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?

Opens with a specific verb and resource ('Permanently delete from Garmin Connect') and then enumerates exactly which record kinds are supported, matching the kind enum one-for-one. An agent can distinguish this from the many garmin_add_*/create_*/upload_* siblings without opening any schema.

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?

States the two-step workflow precisely: without confirm it only previews, with confirm=true it deletes only what was previewed in the last 15 minutes. That is clear when-to-do-what guidance. It stops short of naming exclusions or prerequisites (permissions, what happens if no prior preview exists), so not a 5.

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