Skip to main content
Glama

Set calendar occurrence

set_calendar_occurrence
Destructive

Change ONE occurrence of a calendar event — move it, retitle it, cancel it — leaving the rest of the series as it is; or with reset=true put it back as the rule gives it. Name it by 'eventId' and 'occurrence' as list_calendar_events gives them (the start its rule gives it, e.g. 20261123T150000Z — the same name after a move). What you leave out keeps what it had; a new 'start' alone keeps its length. An event that happens once has one occurrence and is changed the same way. Subscribers' calendars see the change at their next read. Anybody who may write in the project.

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": {
      "project": "<project>",
      "eventId": "<eventId>",
      "occurrence": "<occurrence>"
    },
    "name": "set_calendar_occurrence"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNoIts new end.
batchNoYour own name for a set of changes — e.g. 'solver 2026-11-18' — so rollback_calendar_batch can undo all of them in one call.
resetNotrue to drop every change of this one: it is again as the rule gives it.
startNoIts new start, ISO 8601 (on the event's time zone without an offset).
titleNoIts own title for this one.
sourceNoWho you are, as the history should say it — 'solver', 'bot'. The door (mcp) and your account are recorded anyway.
eventIdYesThe event, as 'eventId'.
projectYesThe project key, e.g. TH.
locationNoIts own place for this one.
cancelledNotrue to cancel this one, false to bring it back.
occurrenceYesThe occurrence, as 'occurrence', e.g. 20261123T150000Z.
confirmOverCeilingNotrue to let this write take a week over the ceiling of reconfigurations — only for somebody who configures the project.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / batch
      Added value: +{
      +  "default": null,
      +  "description": "Your own name for a set of changes — e.g. 'solver 2026-11-18' — so rollback_calendar_batch can undo all of them in one call.",
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • addedInput schema / properties / source
      Added value: +{
      +  "default": null,
      +  "description": "Who you are, as the history should say it — 'solver', 'bot'. The door (mcp) and your account are recorded anyway.",
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
  2. Changed1 schema field changed
    • addedInput schema / properties / confirmOverCeiling
      Added value: +{
      +  "default": false,
      +  "description": "true to let this write take a week over the ceiling of reconfigurations — only for somebody who configures the project.",
      +  "type": "boolean"
      +}
  3. Added

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only flag readOnlyHint=false and destructiveHint=true; the description goes much further by defining partial-update semantics ('What you leave out keeps what it had; a new start alone keeps its length'), the effect on subscribers' calendars ('at their next read'), and the authorization rule ('Anybody who may write in the project'). The reset and cancelled parameters are framed as revert/restore actions, which tells the agent that destructive edits are recoverable in-place.

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 action and its scope are front-loaded in the first clause, and the remaining sentences each carry distinct information (naming, partial updates, single-occurrence events, propagation, permissions). The em-dash-heavy phrasing is dense and the naming/semantics sentence is long, but no sentence is redundant.

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 12-parameter destructive mutation with no output schema, the description covers the important behavioral surface: partial updates, occurrence identification, propagation timing, and write permissions. What it does not address is the return value or how the caller confirms which occurrence was changed, though the batch/rollback parameters in the schema partially compensate.

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 100%, so the baseline would be 3, but the description adds genuinely non-obvious meaning about the 'occurrence' key: it is the start the rule gives the occurrence and remains the same name after a move. That detail cannot be derived from the schema description ('The occurrence, as 'occurrence', e.g. 20261123T150000Z') and prevents a common mis-call.

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?

The opening clause names a specific verb and resource with its crucial scope limiter: 'Change ONE occurrence of a calendar event — move it, retitle it, cancel it — leaving the rest of the series as it is.' That single sentence separates it from a whole-series setter and from deletion, and it enumerates the three operations the tool actually performs.

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?

It says to use list_calendar_events to obtain the 'eventId' and 'occurrence' identifiers, explains the reset=true path for reverting, and clarifies that single-fire events are edited the same way. It does not explicitly name the sibling to use when the whole series should change, but the 'leaving the rest of the series as it is' clause makes that boundary inferable.

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