Skip to main content
Glama
Sign In

Totally Tarot Calculators

by net.totallytarot
OverviewDiscussionsAdmin

Chinese lunar date converter

convert_chinese_lunar_date
Read-onlyIdempotent

Converts a Gregorian date to the Chinese lunisolar calendar or back: lunar year, month, day, whether the month is a leap month, when it began, and the solar term in effect. Takes "date" or "lunar", one of the two.

A month starts on the day, at Beijing time, of its new moon, so tables built in another zone can put months a day off. Placement follows GB/T 33661-2017. Leap months, 2033-2035 and pre-1929 dates come back unverified, with no date.

Results include an attribution line and a permalink.

Input Schema

NameRequiredDescriptionDefault
dateNoGregorian date, ISO YYYY-MM-DD, 1929-3025. Example: "2024-02-10". Neither: today (UTC).
leapNo"yes" if the lunar date is in a leap month; only with lunar. Example: "yes".
lunarNoLunar year-month-day, YYYY-MM-DD, year = Gregorian year of its month 1. Example: "2024-01-01".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • removedInput schema / anyOf
      Removed value: -[
-  {
-    "required": [
-      "date"
-    ]
-  },
-  {
-    "required": [
-      "lunar"
-    ]
-  }
-]
    • changedInput schema / properties / date / description
      Previous value: -"Gregorian date, ISO YYYY-MM-DD, 1929-3025. Example: \"2024-02-10\"."New value: +"Gregorian date, ISO YYYY-MM-DD, 1929-3025. Example: \"2024-02-10\". Neither: today (UTC)."
  2. Added

TDQS

A4.1/5.0
Behavior5/5

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

Annotations already cover read-only/idempotent/non-destructive, and the description goes well beyond them: the Beijing-time new-moon rule for month boundaries, the GB/T 33661-2017 placement standard, explicit failure/uncertainty behavior (leap months, 2033-2035, pre-1929 come back unverified with no date), and the presence of an attribution line and permalink in the response. These are exactly the traits an agent cannot get from structured fields.

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 clause, and the caveat and output paragraphs are short. The second paragraph is compressed almost telegraphically ('Leap months, 2033-2035 and pre-1929 dates come back unverified, with no date'), which costs a little readability but wastes no words.

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?

There is no output schema, yet the description still enumerates the returned fields, the attribution/permalink, and the degradation cases where no date is returned. Combined with the dense boundary-rule note, an agent has everything needed to call this correctly and interpret the result.

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 is 3; the description earns above that by stating the mutual exclusivity of date/lunar ('one of the two'), a constraint the flat schema does not enforce or state. The leap-only-with-lunar rule is repeated from the schema but not expanded further.

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 names a specific verb and resource ('converts a Gregorian date to the Chinese lunisolar calendar or back') and enumerates exactly what the result contains (year, month, day, leap flag, month start, solar term). It does not explicitly distinguish itself from the sibling convert_calendar_date, so an agent scanning siblings still has to infer which converter handles which system.

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?

'Takes "date" or "lunar", one of the two' gives clear intra-tool selection guidance, and the 1929-3025 range is conveyed via the schema. But there is no statement of when to reach for this tool versus convert_calendar_date or get_solar_terms, and no exclusions; usage is only implied.

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

All Totally Tarot Calculators toolsInspect
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