@findtime/mcp-server

rank_recurring_slot

Read-onlyIdempotent

Score a recurring weekly meeting slot across timezones, including daylight-saving weeks, to show which attendees it burdens. Provide weekday, time, home timezone, and locations to compare options.

Instructions

Score who a weekly wall-clock time punishes, including a daylight-saving week when one falls in the next 26 weeks. Use for "Monday 9am PT standup for San Francisco, London, and Bangalore". weekday is a day name. time is a clock such as 9am. home is the IANA timezone of that clock. Paste shareText. The kinder slot and plannerUrl come from the meeting engine. If a week has context, tell the user that sentence. It says whether daylight saving skipped that local time or made it happen twice.

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": {
      "weekday": "<weekday>",
      "time": "<time>",
      "home": "<home>"
    },
    "name": "rank_recurring_slot"
  }
}

Input Schema

Name	Required	Description
`now`	No	Optional ISO instant used as "today" when choosing the next weekday. Defaults to the current time.
`home`	Yes	IANA timezone of the recurring clock, such as America/Los_Angeles.
`time`	Yes	Clock time such as 9am or 09:00 in the home timezone.
`weekday`	Yes	Day name such as Mon or Monday. 1 is Monday and 7 is Sunday.
`workEnd`	No	Last in-hours local hour, inclusive. Default 18.
`locations`	No
`workStart`	No	First in-hours local hour. Default 9.
`_endUserId`	No	Optional opaque per-call end-user attribution token populated by the MCP host, not the LLM. Use a non-PII hash or token; never send raw email, name, or platform user ID.
`occurrences`	No	How many weeks to score before adding a DST week. Default 4. Max 8.
`countryCodes`	No
`durationMinutes`	No	Optional. Only 30, 45, or 60 are written onto the planner link.

Schema Changelog

Changes observed during successful MCP inspections.

Addedv3.28.1Nov 2, 2026

TDQS

A3.5/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds meaningful behavior beyond that: it evaluates a DST week when one falls within 26 weeks, and it tells the agent what to relay back (shareText, the kinder slot, plannerUrl, and the per-week context sentence about skipped or doubled local times). This is valuable output-handling guidance that annotations do not supply. It stops short of saying how the ranking itself is computed or what the numeric scores look like.

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

Conciseness3/5

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

The purpose and example are front-loaded, which is good. But several sentences are clipped to the point of ambiguity: 'Paste shareText' and 'The kinder slot and plannerUrl come from the meeting engine' read as fragments whose object and action are unclear without external knowledge. The final sentence about DST context is clear but sits after the choppier ones.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description carries the burden of explaining return values; it partly does by naming shareText, the kinder slot, plannerUrl and the week context sentence. But with 11 parameters it leaves locations, countryCodes, workStart/workEnd and occurrences entirely to the schema, and it never states the shape of the ranking result. Adequate for the headline behavior, thin for the full surface.

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?

With schema description coverage at 82%, the schema already documents weekday, time, home, now, occurrences, workStart/workEnd and durationMinutes. The description mostly restates those three required fields ('weekday is a day name', 'time is a clock such as 9am', 'home is the IANA timezone'), adding only the relational note that home is the timezone of that clock. It says nothing about locations, countryCodes or how occurrences interacts with the DST week, so it does not beat the baseline.

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 verb-plus-resource is unusual but discernible: it scores a recurring weekly wall-clock meeting slot by how badly it lands across timezones, and it adds DST handling as part of the scope. The concrete example ('Monday 9am PT standup for San Francisco, London, and Bangalore') makes it distinguishable from siblings like find_meeting_time and check_proposed_time. The metaphors 'punishes' and 'kinder slot' keep it from being fully crisp.

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

Usage Guidelines3/5

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

The example implies the intended case: a recurring weekly meeting across multiple cities, as opposed to one-off overlap checks. However, it never explicitly says when to choose this over find_meeting_time or check_proposed_time, and there are no stated exclusions or prerequisites. Usage is inferable rather than specified.

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

Deploy Server