syllabus-calendar-mcp

Build an ics calendar

build_ics

Create a valid .ics calendar file from dated events and recurring classes, excluding holidays and reading weeks and adding reminders.

Instructions

Build a valid .ics calendar file from dated events and recurring classes, with reminders. Inputs: events (each with title, date, optional start_time, end_time, type, course, location and notes), classes (each with course, weekdays, start_date, end_date, start_time and optional end_time, location, holidays and reading_weeks), reminders_minutes (whole minutes before each event, default 60), calendar_name and optional output_path. Each class becomes one weekly recurring event with holidays and reading weeks removed. The tool checks the file before returning it. Example prompt: "Make an .ics file for my course with a reminder one day before each assignment."

Input Schema

Name	Required	Description
`events`	No	Dated events such as assignments and exams.
`classes`	No	Recurring classes to add as weekly events.
`output_path`	No	Optional file path. When it is passed, the calendar is written there as a .ics file.
`calendar_name`	No	Name shown in the calendar app. Defaults to "Course calendar".
`reminders_minutes`	No	Reminder times in whole minutes before an event. Defaults to [60]. Pass an empty array for no reminders.

Output Schema

Name	Required	Description
`ics`	Yes	The calendar file as text, with CRLF line breaks.
`valid`	Yes	True when the calendar passed the built in checks.
`errors`	Yes	Problems found by the checks. Empty when the calendar is valid.
`class_count`	Yes	How many recurring classes the calendar holds.
`event_count`	Yes	How many single events the calendar holds.
`output_path`	Yes	The file path the calendar was written to, or null when no path was passed.
`class_meetings`	Yes	How many class meetings the recurring events produce after skips.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 30, 2026

TDQS

A3.6/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=false and openWorldHint=false, so the write-local scope is known. The description adds real behavior beyond that: each class becomes one weekly recurring event with holidays and reading weeks removed, and 'the tool checks the file before returning it.' What it omits is what happens when output_path is not supplied (file content returned vs. nothing), which is the key behavioral ambiguity for a caller.

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?

Purpose is front-loaded in the first sentence, then inputs, then behavior, then an example. The middle sentence is a long run-on enumeration of inputs, but each element maps to a distinct parameter and nothing is redundant with the surrounding sentences.

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?

With an output schema present, return values need no explanation, and the description covers inputs, defaults, recurrence expansion, holiday exclusion, and validation. The only meaningful gap is the no-output_path case. Comfortable for a 5-parameter optional-only tool.

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 the schema already documents every parameter, nested item field, formats, and defaults. The description's parameter enumeration mirrors the schema rather than adding new semantics. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a precise verb and resource: 'Build a valid .ics calendar file from dated events and recurring classes, with reminders.' The input enumeration makes it clear this is the construction step, not extraction or merging. It never names the siblings (extract_schedule_events, expand_recurring_classes, merge_calendars), so the differentiation is inferred rather than stated.

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?

The concrete example prompt ('Make an .ics file for my course with a reminder one day before each assignment') anchors when this tool applies, and the defaults documented for reminders_minutes and calendar_name give calling context. There is no explicit when-not guidance or routing to the sibling tools, so it stops short of a 5.

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

Deploy Server