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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds real behavioral detail: the nulling of houses/angles/sect under timeUnknown, the supplementary timeUnknown block describing the Moon's daily range, and the localization overlay behavior. It does not mention the 20-credit cost or any rate limits, which would have been useful for an agent weighing calls.

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?

Three sentences, all working: purpose first, then the timeUnknown branch, then localization. No filler. It is dense and the ?lang= sentence is slightly cryptic, but every sentence carries load and the most important information leads.

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 16-parameter, 20-credit tool, the description covers the headline capability and the most consequential branch, which is the right instinct. But with an output schema present it wisely skips return-value narration, leaving the main remaining gap the unexplained configuration surface (house-system codes, zodiacType, ayanamsa selection) that an agent will otherwise have to guess at.

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 only 31% across 16 parameters, so the description needs to compensate. It supplies meaningful semantics for timeUnknown (undefined in the schema) and for the time-vs-timeUnknown branch, plus the ?lang= localization parameter that does not even appear in the schema. However, ten-plus parameters (zodiacType, houseSystem's opaque enum codes, cosmogram, ayanamsaId, city, name) get no explanation from either source.

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?

States a specific verb and resource ('Calculate a full natal chart') and enumerates the payload (planets, house cusps, aspects, sect, angular data), which implicitly separates it from narrower siblings like astroway_western_planets or astroway_western_ephemeris. It never names an alternative tool, so the differentiation is left to inference rather than made explicit.

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 one usage rule given is internal to the tool ('when the birth time is unknown, send timeUnknown: true'), which is really parameter guidance rather than tool-selection guidance. There is no statement of when to prefer this over astroway_western_planets, astroway_render_wheel_western, or the horoscope siblings, so selection is only implied.

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