Skip to main content
Glama

Add or update events

upsert_events
Destructive

Adds or updates up to 20 calendar events the athlete tells you about (match, tournament, coach_session, travel, rest, other; set_rest_day also makes rest events; dates YYYY-MM-DD, end inclusive). Omit id for a new event (the server makes the id); pass the id you got back to change or cancel one of your own (status "cancelled"). An id that doesn't exist is skipped. Events are never deleted. You can't change events the athlete created, and you can't set a cancelled event back to active; if it's back on, add it again as a new event. You can still edit a cancelled event's title or dates if you leave status out. Those come back in skipped with the reason. The app only acts on a rest event (the day becomes a rest day). Every other event is stored as context and changes no session.

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": {
      "events": "<events>"
    },
    "name": "upsert_events"
  }
}

Input Schema

NameRequiredDescriptionDefault
eventsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Goes well past the annotations: it discloses that events are never deleted, that unknown ids and disallowed edits return in `skipped` with a reason, that athlete-created events are immutable, that cancelled events accept title/date edits only when `status` is omitted, and that only rest events affect the app while all others are inert context. This is exactly the kind of write-scope detail destructiveHint=true alone cannot convey.

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?

Dense but every sentence conveys a real rule, and the core upsert behavior is front-loaded in the first two sentences. The tail end drifts into a slightly tangled order — the `skipped` behavior is mentioned before the edit rules that produce it — but there is no filler.

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 bulk-write tool with no output schema and a nested event object, it covers creation, update, cancellation, rejection, and side effects on the app thoroughly, and it hints at a returned payload ('the id you got back', the `skipped` array). What the full response contains is only implied rather than described.

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?

With 0% schema description coverage the description carries the whole burden and does: it lists all six `kind` values, fixes the `YYYY-MM-DD` format, adds the non-obvious 'end inclusive' semantics, explains the `id` lifecycle, and specifies `status: "cancelled"` as the cancellation mechanism. Only the title length cap is left to the schema.

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 and resource ('Adds or updates up to 20 calendar events') and immediately enumerates the event kinds and the id-based upsert rule. An agent can distinguish this from set_rest_day or set_today_session without opening a 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?

Gives clear when-to-do-what guidance: omit `id` for creation, pass a returned id to change or cancel, re-add as a new event if something must become active again. It references set_rest_day as an overlapping alternative ('set_rest_day also makes rest events') but never states explicitly which tool to prefer when both could apply, so it stops short of full alternative routing.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources