Skip to main content
Glama

Find a time for a circle

circles_free_times_find
Read-only

Find when everyone in one of the person's circles - family, friends or a team - is free or available: each stretch of a window that no member's busy time touches and that is at least as long as the meeting, in the zone the call names, else the person's own - the same whichever member asks, save for a member with no calendar connected, counted by the asker's own polls. The calendars each member owns and counts as busy - never one someone else shared with them - are read through that member's own connection as the call is made, and come back under busy only as when that member is busy - the circle's owner named owner, every other member by the address invited - never what an event says. An event holds its time as its provider's own free/busy shows it: on Google unless shown as available or declined - an invitation not yet answered or answered maybe included - on iCloud or a calendar server unless shown free or declined, and on Outlook only when shown busy or away, so an Outlook tentative answer leaves its time free; a cancelled event holds none. An all-day event holding time holds its whole day in its member's time zone; no one's stored working hours or other preferences apply, only the hours and weekdays the call names, in the answer's zone; limit keeps the earliest stretches, and the search keeps to the window's first 365 days. A member none of whose calendars could be read is named under unknown, and one only some of whose could under readInPart, their busy time read counted; either's busy time may fall inside a stretch. A member with no calendar connected counts as free only at the times they ticked in the person's own polls for this circle, and until they answer one is named under noCalendar - polls_create naming the circle asks them. On the person's own circle each address invited that has not joined is named under notJoined and counts the same way once it answers such a poll. Anyone counted by polls whose answers tick no time in the window is named under tickedNothing. Each stretch names under members every other member's own time for it in the zone they stored, marked unusual where any of it falls outside 09:00-18:00 or on a Saturday or Sunday there. circles_list names each circle's id. Any of the person's own accounts needing reconnection is named under unread, another member's never. An account named under unread as needs_reconnection carries its own row under reconnectAt, where the person, signed in as the same account, presses "Reconnect"; calls to it answer again only once they have.

Input Schema

NameRequiredDescriptionDefault
toYesEnd of the window, excluded, with its offset.
fromYesStart of the window, included, with its offset, e.g. 2026-10-12T09:00:00+01:00.
hoursNoOnly these hours of each day, e.g. 10:00-16:00 or 09:00-12:00, 14:00-17:00.
limitNoAt most this many stretches, the earliest.
circleYesThe circle's id, as circles_list names it.
minutesNoMeeting length in minutes; the stored one where omitted.
timeZoneNoAn IANA zone such as Europe/London the answer is given in; the stored one where omitted.
weekdaysNoOnly these days of the week.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior5/5

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

With readOnlyHint=true and destructiveHint=false already covering safety, the description adds extensive behavioral context beyond annotations: provider-specific free/busy interpretation, all-day event handling, working-hours exclusion, 365-day search limit, unknown/readInPart/noCalendar/notJoined statuses, poll-based counting, reconnect requirements, and output member annotations.

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

Conciseness2/5

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

The description is a very long, dense, run-on block with minimal structure. While many details are useful, it is not appropriately sized or easy to parse, and much of the provider-specific detail could be organized more concisely.

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?

Even without an output schema, the description thoroughly covers return semantics: busy times, owner naming, member time zones, unusual markers, unknown/readInPart/noCalendar/notJoined/tickedNothing/unread statuses, and reconnectAt details. This is sufficient for an agent to understand the response structure.

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 all eight parameters. The description adds some context such as the 365-day window limit and provider free/busy rules, but it does not substantially deepen per-parameter meaning beyond what the schema provides.

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?

The description states a specific verb and resource: find when everyone in one of the person's circles is free or available, with defined window, duration, and zone semantics. It does not explicitly distinguish this tool from the sibling free_times_find, so sibling differentiation is missing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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

The description explains behavior in depth but gives no explicit guidance on when to use this tool versus alternatives such as free_times_find. It references circles_list for ids and polls_create for poll-based members, but those are supporting actions rather than routing guidance.

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.