Phase Return

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

Annotations already declare readOnly, idempotent, non-open-world and non-destructive, so the safety profile is covered and the description is not required to restate it. What the description does add is genuinely useful operational context: the endpoint, the group, and a 100-credit Tier 4 cost, which lets an agent weigh the call against cheaper siblings. It says nothing about how far ahead the search reaches, how results are bounded, or why a location-dependent input is required for an ostensibly phase-based query.

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?

A single front-loaded sentence carries the whole definition, followed by three compact bracketed metadata fields. There is no filler. The only slight cost is that the metadata lines sit at the same visual weight as the purpose statement rather than after it, but the total length is well controlled.

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?

An output schema exists, so return values need no explanation, and the annotations cover safety. However, the definition omits two things an agent needs: how the target planet/phase is chosen given no such parameter, and why natal latitude/longitude are mandatory for a synodic-phase search (presumably event visibility is location-dependent, which is never said). For a 100-credit Tier 4 call, that is a meaningful shortfall.

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 effectively complete, with rich field-level prose on timezone, ayanamsa, houseSystem and coordinate naming, so the schema carries the parameter burden and a baseline 3 applies. The description adds nothing beyond that and, notably, leaves the most consequential semantic question open: the schema exposes no planet field or phase-type selector, so it is unclear how the 'planet' and target phase named in the description are actually specified.

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 (find dates) and a precisely defined astronomical resource (a planet returning to the same synodic phase relative to the Sun), with two concrete worked examples that remove ambiguity about what a 'phase return' is. It is distinguishable from generic return/phase siblings by the 'synodic phase relative to the Sun' framing. What it does not state is how the planet itself is selected, since 'a planet' is referenced but no planet selector appears in the schema.

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 examples ('next Venus heliacal rising, next Mars retrograde station') imply the kind of question this answers, which is a reasonable usage signal. But there is no explicit when-to-use vs when-not guidance, no mention of the near neighbours it overlaps with (astroway_prognostics_planetary_return, astroway_calendar_planetary_phases, astroway_hellenistic_schmidt_stations_and_phases), and no note on when a simpler ingress/calendar tool would suffice.

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