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

Annotations already declare readOnly, idempotent, non-destructive, so the safety profile is covered. The description adds genuinely useful behavior: the server auto-computes the transit date from location coordinates, and daily cadence returns astronomical_time_windows and panchang_timing. It stops short of describing pagination, error behavior, or the shape of the forecast output itself.

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?

Long but front-loaded: purpose first, then cadences, then mandatory params and the critical date-handling warning. Every sentence carries operational content, though the MANDATORY/CRITICAL emphasis blocks make it denser than strictly necessary.

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 14-param tool with an output schema, the description covers cadence semantics, required inputs, the birth_date pitfall, and the no-invented-hours constraint. The residual gap is the ambiguity among city/current_city/target_city and date/time params, which the agent must still infer from names alone.

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 0% across 14 parameters, so the description must carry the load. It does disambiguate the two highest-risk params (birth_date vs target_date) and documents birth_city, current_city, cadence, and user_prompt. However, city, date, time, target_city, birth_time, birth_country, and current_country are never mentioned, leaving a confusing cluster of similarly named location/date fields unexplained.

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+resource (generate a personalized transit horoscope with time-windows and strategic forecast) and names the exact commands it maps to (/horoscope, /daily). It is clearly distinguishable from siblings like calculate_chart or get_yogas, which do not produce cadence-based transit forecasts.

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?

Explicitly enumerates the four cadences with what each returns, states the mandatory parameters, and gives a strong when-not rule ('NEVER pass today's date into birth_date') with the correct alternative (target_date) for future dates. This is exactly the routing guidance an agent needs.

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