Skip to main content
Glama

Kaalshodh — Indian astronomy time machine

by com.kaalshodh

get_astro_events

Read-only
Return precomputed astronomical events between start_date and end_date —
any range within years -5000..+5000 (eclipses -1999..3000), instant.

Events are global (location-independent) and served from binary-searched
lookup tables — no live ephemeris computation.

Example questions: "planetary events this month", "solar eclipses in the
12th century", "when was Shani retrograde in 1500 BCE?", "adhik maas
years this decade".

Ritu/ayana changes are Sayan sankrantis: Surya entering Meena=Vasanta,
Vrishabha=Grishma, Karka=Varsha (=Dakshinayan start, = solstice),
Kanya=Sharada, Vrishchika=Hemanta, Makara=Shishira (=Uttarayan start,
= solstice) — query event_types=["sankranti"] with ayanamsa="Sayan".

Args:
    start_date: Start date inclusive, YYYY-MM-DD (e.g. "2026-01-01");
                negative years allowed (e.g. "-3101-01-01")
    end_date:   End date inclusive,   YYYY-MM-DD (e.g. "2026-12-31")
    ayanamsa:   "Lahiri" (Vedic sidereal, default) or "Sayan" (tropical/Western)
    grah:       Optional planet filter. One of: Surya, Chandra, Mangala, Budha,
                Guru, Shukra, Shani, Rahu, Ketu
    event_types: Optional list of event type filters. Valid values:
                "transit"          – Mangala..Ketu change rashi (NOT Surya/Chandra)
                "sankranti"        – Surya changes rashi (~monthly)
                "moon_transit"     – Chandra changes rashi (~monthly)
                "full_moon"        – Purnima (Moon at 180° elongation)
                "new_moon"         – Amavasya (Moon at 0° elongation)
                "retrograde_start" – planet turns retrograde
                "retrograde_end"   – planet resumes direct motion
                "equinox"          – Vernal or Autumnal equinox (Sayan Surya)
                "solstice"         – Summer or Winter solstice (Sayan Surya)
                "asta_start"       – planet enters combust zone (Grah Asta)
                "asta_end"         – planet exits combust zone (Uday)
                "solar_eclipse"    – solar eclipse (catalog, years -1999..3000)
                "lunar_eclipse"    – lunar eclipse (catalog, years -1999..3000)
                "kaal_sarp"        – Kaal Sarp window (interval)
                "adhik_maas"       – intercalary Hindu month (interval)
                "kshay_maas"       – lost Hindu month (interval)
                "kumbh_mela"       – Kumbh Mela window (interval)

The max range is set by the densest requested type: 3 years by default,
up to 1000 years for sparse-only queries (kumbh, maas). Interval events
also carry end_time, duration_days, and type-specific details.

Returns:
    Dict with keys: start_date, end_date, ayanamsa, count, events (list).
    Each event has: time (UTC ISO), event_type, grah, from, to, and
    (for intervals) end_time, duration_days, plus a details dict.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
grahNo
ayanamsaNoLahiri
end_dateYes
start_dateYes
event_typesNo

TDQS

A4.8/5.0
Behavior5/5

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

The description goes beyond the readOnlyHint annotation by disclosing the precomputed, binary-searched lookup-table nature, global scope, no live computation, inclusive date semantics, negative year support, and eclipse year catalog limits. It also explains that interval events carry end_time and duration_days, providing behavioral detail not present in annotations.

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?

Although long, the description is efficiently structured with an intro, example questions, an important Sayan sankranti clarification, an Args section, and a Returns section. Each sentence carries useful information, and the most critical facts (precomputed, global, date range) are front-loaded.

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?

For a complex tool with 5 parameters and no output schema, the description fully explains return keys, event fields, interval details, range constraints, and special semantic notes (e.g., Ritu/ayana changes). It is complete enough for an agent to invoke the tool correctly without additional sources.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description compensates fully by documenting every parameter: start_date/end_date formats with negative year examples, ayanamsa options, grah planet list, and a comprehensive enumeration of valid event_types with meanings. This adds far more meaning than the bare schema.

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?

The description opens with a specific verb-resource pair: 'Return precomputed astronomical events between start_date and end_date', and clearly states the supported year range and that events are global and instant. It also distinguishes itself from siblings like get_planetary_positions by highlighting lookup-table-based precomputation versus live ephemeris.

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 description provides concrete usage context: example questions, the note that events are location-independent, the special Sayan sankranti mapping, and range limits based on requested event types. However, it does not explicitly name alternatives or state 'use get_planetary_positions for live positions', making it slightly below the explicit when/when-not/alternatives bar.

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

All Kaalshodh — Indian astronomy time machine toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.7/5.0
Disambiguation5/5

Each tool targets a distinct query type: planetary conjunctions, panchang date matching, event lists, nearest events, and position snapshots. Even the similar-looking get_astro_events and get_nearest_event are clearly differentiated by range vs. nearest-neighbor scope.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern: find_copresence, find_matching_dates, get_astro_events, get_nearest_event, get_planetary_positions. 'find_' for search operations and 'get_' for retrieval operations, with snake_case throughout.

Tool Count5/5

Five tools is well within the ideal 3-15 range for a domain-specific server. Each tool covers a meaningful, non-redundant capability for astronomical and panchang time travel, and there is no bloat or triviality.

Completeness4/5

The set covers major workflows: positions, events, conjunctions, and panchang-based date search. The only notable gap is a direct 'panchang for a specific date' lookup, which find_matching_dates cannot handle without constraints and which is explicitly delegated to another MCP server. This is a minor workaround rather than a dead end.

Resources