Hindu calendar: vrats (Ekadashi with parana, Pradosh, Sankashti, Purnima, Amavasya, Masik Shivaratri)

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

Annotations already declare the operation as a safe, idempotent, closed-world read, so the safety profile is covered. Beyond that the description does add real behavioral substance: the Smarta vs Vaishnava Ekadashi resolution rules, the Dashami-viddha refusal, and the parana window constraints. That is meaningful edge-case disclosure, though it is confined to one of the six vrat types and says nothing about ordering, completeness of the returned year, or how DST/latitude edge cases are handled.

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

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

The purpose is front-loaded in the first clause, which is good, but it is immediately followed by a single sprawling sentence of dense nested parenthetical jargon about Ekadashi rules. The length is heavily skewed to one vrat type while the other five named in the title get zero prose, so space is not allocated where an agent needs it.

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

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

With an output schema, full annotations and a 88%-covered input schema, the definition does not need to explain return values or most parameters. What is missing is coverage of the non-Ekadashi vrat types promised by the title and the types filter, leaving an agent unable to tell what pradosh, sankashti, purnima, amavasya or masik-shivaratri results will contain.

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

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

Schema description coverage is 88%, so parameters like year, latitude, ayanamsa and timezone are already well documented in the schema. The description adds no parameter meaning beyond restating year/latitude/longitude as required; it never explains the types filter or the ayanamsa choices in prose. Baseline 3 is appropriate when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The opening clause 'Every vrat of the year for the place' gives a specific verb (compute/list), resource (vrats) and scope (for a given location and year), and the title enumerates the six types. However, the body then describes only Ekadashi, and nothing distinguishes this from the sibling astroway_vedic_calendar_festivals, so an agent must infer the boundary itself.

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

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

There is no when-to-use / when-not-to-use guidance and no alternative named; the sibling festivals calendar is never mentioned. The only implicit guidance is the metadata line listing required params and the types filter described in the schema, which is structural rather than advisory.

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