Skip to main content
Glama

delete_custom_food

Destructive

Permanently removes a custom food from the Garmin nutrition library after a preview and explicit confirmation, so you can clean up entries you no longer need.

Instructions

Delete a custom food from the user's Garmin nutrition library

    Permanently removes a custom food entry — this cannot be undone and
    the deleted food's name/brand/nutrition data cannot be recovered from
    the API afterward. The default call previews the food without deleting
    it. Review that preview, then call again with confirm=true.

    Deleting a food does NOT require it to be unreferenced: existing food
    log entries that already reference this food are NOT blocked or
    removed — they remain in the log (their nutrition still counts toward
    daily totals) but are marked inactive (foodInactive: true) and can no
    longer be edited/re-logged from the library.

    Use get_custom_foods to find the foodId, and match on the exact
    foodId (not just a name search) — Garmin's search can return loosely
    related results for a given search term, not just exact matches.

    Args:
        food_id: ID of the custom food to delete — a 32-char hex string
            (from get_custom_foods or create_custom_food)
        confirm: Set true to delete after reviewing the default preview
    

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": {
      "food_id": "<food_id>"
    },
    "name": "delete_custom_food"
  }
}

Input Schema

NameRequiredDescriptionDefault
confirmNo
food_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true and idempotentHint=false, yet the description adds substantial context: irreversibility and unrecoverable data, the preview/confirm gating behavior not captured by annotations, and the non-obvious side effect that existing log entries survive but become inactive while still counting toward totals. It also clarifies that unreferenced status is not required.

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?

The irreversible/destructive fact and the preview flow are front-loaded, and each paragraph addresses a distinct concern. The trailing Args block restates flow details already stated above, adding modest redundancy, but nothing is superfluous enough to impair use.

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 destructive two-parameter tool with no output schema, the definition covers safety, prerequisites, side effects on related data, and parameter formats. An agent has everything needed to call it correctly and to avoid an accidental irreversible deletion.

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 carry the full burden and does: food_id is documented as a 32-char hex string with its sources, and confirm is documented as the post-preview deletion trigger with its default-preview semantics implied. No parameter is left ambiguous.

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+resource ("Delete a custom food from the user's Garmin nutrition library") and implicitly distinguishes itself from delete_food_log by emphasizing it removes a library entry, not log entries. An agent can identify the target object without opening the schema.

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?

Gives an explicit two-step workflow (the default call previews; review, then call with confirm=true) and names the prerequisite tool get_custom_foods for obtaining the foodId. It also warns to match on exact foodId rather than name, a concrete usage constraint the agent would otherwise miss.

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