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

Beyond the annotations (readOnly/idempotent/non-destructive/closed-world), the description discloses high-value behavior an agent cannot infer: this is a paid endpoint ($0.01 USDC on Base via x402, HTTP 402 then retry with PAYMENT-SIGNATURE), the 5-year-per-call cap, UTC minute precision, and the underlying ephemeris coverage window (JPL DE421, 2025–2030). The payment flow and data-coverage bound are exactly the operational facts the annotations do not carry.

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, front-loaded with the deliverable, then constraints, then pricing. The first sentence is long and dense but every clause names a distinct event type or output shape. The 'astronomical timing, not a horoscope' line is short and prevents a domain misread, so it earns its place.

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?

There is no output schema, so the description carries the return shape and does so ('sorted event list plus the cycles they belong to'). It also states price, payment mechanics, time span limits and the ephemeris date window — everything needed to call this correctly and to anticipate a 402 payment round-trip.

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 100%, so the schema already documents `from`, `to` and the planet enum including their defaults. The description adds only marginal semantics — the 5-year ceiling and the one-year default span — while restating UTC precision. Baseline 3 is appropriate when the schema carries the parameter burden.

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 resource (retrograde-cycle events for eight named planets) and enumerates the event types returned (pre-shadow, station retrograde, cazimi/opposition, station direct, post-shadow) over a date range. It also distinguishes itself from the siblings is_planet_retrograde / next_planet_retrograde by positioning itself as the range/cycle tool versus 'current status' and 'next retrograde'.

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?

"Free tools cover the current status and the next retrograde" gives an explicit when-not-to-use signal and points at the alternative class of tools. It does not name the specific siblings (retrograde_planets_today, next_planet_retrograde, planet_retrograde_dates), so an agent must still map the category to a name, but the selection context is clear.

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