FullClass

Get attendance rates

get_attendance_rates

Read-onlyIdempotent

Whether booked guests showed up: seats booked, seats checked in and no-shows, for events that have already finished between start_date and end_date, grouped by class (default, worst attendance first), instructor, location or month. With no dates it covers the 30 days ending today. Only checked-in guests count as attended, so an event where check-in was never done reads 0%. For how many seats sold against capacity, use get_fill_rates.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_attendance_rates"
  }
}

Input Schema

Name	Required	Description
`end_date`	No	last day to include, inclusive, YYYY-MM-DD; when left out it is today, or the 30th day from start_date when only start_date is given
`group_by`	No	class, instructor, location, or month; defaults to class
`start_date`	No	first day to include, YYYY-MM-DD in the studio's timezone; when left out the window is the 30 days ending on end_date

Output Schema

Name	Required	Description
`to`	Yes
`from`	Yes
`note`	Yes
`booked`	Yes
`events`	Yes
`groups`	Yes	worst attendance first, or chronological when grouped by month
`attended`	Yes
`group_by`	Yes
`no_shows`	Yes
`timezone`	Yes
`truncated`	No
`attendance_percent`	Yes	attended as a percentage of booked

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedNov 5, 2026

changedInput schema / properties / group_by / description

Previous value: -"class or month; defaults to class"New value: +"class, instructor, location, or month; defaults to class"

changedOutput schema / properties / groups / description

Previous value: -"worst attendance first when grouped by class"New value: +"worst attendance first, or chronological when grouped by month"

changedOutput schema / properties / groups / items / properties / group / description

Previous value: -"the class name, or the month as YYYY-MM"New value: +"the class, instructor or location name, or the month as YYYY-MM; (no instructor) and (no location) collect events without one"

First observedNov 5, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, and the description still adds a genuinely valuable data-semantics warning that a never-checked-in event reads 0% attended. It also discloses the default 30-day window and the default ordering (worst attendance first), which are not safety-related but shape interpretation of results.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four sentences, each doing distinct work: what is measured, the default window, the check-in caveat, and the sibling route. The metric definition is front-loaded and nothing is redundant with the schema.

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?

Output schema exists, so return-shape explanation is unnecessary, and all three optional parameters plus their default windows are accounted for. For a zero-required-parameter reporting tool, nothing an agent needs in order to call it and interpret it correctly is missing.

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 defaults for start_date/end_date/group_by are already documented; the description adds the non-schema detail that grouping defaults to class and that classes are ordered worst attendance first. That ordering cannot be inferred from the schema and materially changes how output is read.

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 the exact resource (attendance: seats booked, checked in, no-shows) and the scope (finished events only, bounded by start_date/end_date), plus the grouping options. The closing sentence explicitly separates it from get_fill_rates, so an agent can pick correctly 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 Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a clear use condition implicitly ('events that have already finished') and names one alternative with its selecting condition: capacity questions go to get_fill_rates. It does not address the other plausible siblings such as get_booking_summary or list_underfilled_events, so routing for those is left to inference.

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

All FullClass tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?