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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive behavior. The description adds valuable context beyond these: 'No auth required; free commercial use' and the explicit 'max 365 days per call' limit. It also discloses the output shape (array of daily records with listed fields). No contradictions with annotations; this is strong supplementary disclosure.

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?

The description is reasonably concise, front-loading the core purpose, then output, use cases, format, and auth. There is slight redundancy ('up to 365 days' appears twice, 'date range' repeated), but overall it is efficient and well-structured. Could be tightened without losing clarity.

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 6 parameters, an output schema, and a read-only operation, the description covers the essential aspects: purpose, output fields, use cases, date format, range limit, auth, and source. It does not mention the timezone auto-detection or time_format defaults, but these are already in the schema. It is complete for an agent to call correctly, though it could explicitly note the single-day alternative.

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 all parameters are documented in the schema. The description reinforces the date format and range limit ('Specify date_start and date_end in YYYY-MM-DD format; max 365 days per call'), but this largely duplicates schema info (e.g., date_end description already mentions max 365 days). It adds minimal new semantic value beyond the schema, so baseline 3 is appropriate.

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 opens with a specific verb ('Get'), a concrete resource ('sunrise/sunset/moon phase data'), and a clear scope ('date range of up to 365 days for any global coordinate'). It explicitly mentions the range capability, distinguishing it from sibling tools like sunrisesunset.astronomy.daily (single-day) and sunrisesunset.moon.phase (moon-specific). The purpose is unambiguous.

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 description provides use-case context (seasonal planning, photography, agriculture, event scheduling) but does not explicitly instruct when to prefer this tool over its siblings (e.g., 'for a single day use sunrisesunset.astronomy.daily'). It implies the range use case but lacks direct alternative routing, leaving some inference to the agent.

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