get_current_sky

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description still adds real behavioral context: server-side checks run before successful results are returned, detail_level=summary truncates object/nested rows to five while preserving scalar lists and marking omissions, and verification references always point at the full checked calculation. The main gap is that it doesn't describe the shape/density of the full payload beyond field names.

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?

Purpose and scope are front-loaded, but the paragraph then piles on verification workflow, sibling-redirect rules, and a full restatement of detail_level semantics already present in the schema. For a three-parameter read tool this is over-long, and several sentences (e.g. the 'do not ask for a city' admonition) would be better placed in the agent protocol.

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?

With no output schema, the description does the necessary work: it lists the returned content categories, explains the summary/full truncation tradeoff, and states the default moment. It stops short of describing the structural shape of nested results (e.g. aspect or station records), which leaves a modest gap for an agent planning to consume the output.

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 67% and the description compensates for the undocumented `moment` parameter by specifying ISO 8601 with an offset and a 'now' default. It also adds behavior for `include` (retrograde_planets returns only retrograde planets plus their next direct station) beyond the schema's field list, though it references `stations_today`, which is not among the schema's enumerated selectable fields — a small inconsistency.

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 computation ('Sky at one moment') and enumerates exactly what the result contains: lunar phase, Moon sign, void-of-course window, lunations/eclipses, retrograde planets, stations and aspects. It also carves out its scope against siblings ('no birthplace or geographic location required', 'not a complete annual retrograde calendar'), letting an agent separate it from the natal/house-chart and render_* tools without opening any 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?

Gives explicit routing rules: defaults to now, use include=retrograde_planets for retrograde-only output, stations_today is limited to the Beijing calendar day, and for yearly requests to explain the limit rather than switching to a house chart or asking for a city. It also mandates calling verify_calculation_claims before interpreting results, which is a concrete when-to-use instruction with a named sibling.

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