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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: the reversed-degree handling of Rahu, the exclusion of Ketu from both schemes, the fact that the two schemes may yield different Atmakaraka names, and the exact office ordering hierarchy. It does not describe response format or states/environments such as throttling, but for a read-only deterministic calculator this is substantial added context.

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 core functional explanation is well ordered: ranking rule first, then the Atmamakra, then the office assignments, then the seven-vs-eight scheme distinction. However, the trailing keyword farm ('AtmAkaraka calculator API, Darakaraka, Jaimini chara karaka, Vedic astrology soul-влека') adds noise repeated from the text without an informational value for an agent, and the prose is dense with astrological terminology that could be pruned for agent utility. It is reasonably sized but not genuinely concise for agent consumption.

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?

For a complex astrology tool with 10 parameters, 3 enums, 4 required fields, and no output schema, the description covers the core domain concepts an agent needs: what the computation ranks, the two schemes, the Karile offices in order, the Rahu/Ketu specifics, and the relevance of reference-software conformance. It doesn't state response shape or pagination/token behavior, but the karams and scheme details plus the exhaustive schema documentation largely close the comprehension gap, and the compact parameter field addresses token usage explicitly.

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 coverage is 100%, so the parameters themselves ('date', 'time', 'latitude', 'longitude', 'scheme', 'ayanamsa', etc.) are all individually documented, putting the baseline at 3. The tool description does enrich the meaning of the scheme parameter (fuller explanation of seven vs. eight, Rahu's reversal, Ketu's exclusion), which adds value over the schema description. It does not, however, clarify the relationship between parameters like ayanamsa vs ayanamsaValue or timezone variants more than the schema already does, so no bonus above baseline.

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 description names a specific verb ('Calculate'), a specific resource ('Chara Karakas of Jaimini astrology'), and a concrete input ('from birth details'). It goes further by explaining the ranking rule (by how far each graha has advanced into its sign), who the Atmakaraka is, and the eight offices in descending order, so an agent cannot mistake this for the other Vedic astrology endpoints. The ATMAKARKA-centric title further disambiguates it from the many sibling calculators.

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?

The description gives clear, actionable context: the tool is for deriving the Atmakaraka/soul significator and the remaining seven Jaimini Chara Karaka offices from birth details, and it explicitly advises selecting seven vs eight schemes 'based on what your reference software uses' while warning the two can name a different Atmakaraka for the same chart. It does not explicitly name sibling tools to exclude, which keeps it from a 5, but the intended circumstances of use are unambiguous.

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