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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, yet the description still adds real value: the ±1 day accuracy caveat, the deterministic-output guarantee, and concrete limits (64 KB input, 1 s per call, 1 MB result). The accuracy disclosure is the kind of trait an agent cannot get from structure. Minor deduction because the side-effect/determinism statements largely restate the annotations.

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 Cuando / No para / Efectos / Límites structure is scannable and front-loads the purpose, but the content is delivered twice in full (ES then EN) and then a third time verbatim via the schema description, and several sentences merely restate the annotations.

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 single-parameter, read-only computation with an output schema and full annotation coverage, this is essentially complete: purpose, accuracy, limits and the sibling exclusion are all present. The one gap is the misleading "when" clause, which points at DST/calendar exactness rather than at actual moon-phase use cases.

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 100% with a single required parameter, so the baseline is 3. The description adds conceptual meaning (the instant is measured against a fixed reference new moon) but does not clarify the accepted datetime format or timezone handling beyond what the schema's example shows.

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 and resource (computes approximate moon phase for an instant) and enumerates the outputs: age in days, illuminated fraction, phase name in en/es. It also names the algorithm basis (mean synodic month since the 2000-01-06 18:14 UTC new moon) and accuracy (±1 day), which no sibling covers.

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 exclusion is excellent: "No para: calcular la salida y puesta del sol... (sun-times)" explicitly names the closest sibling and the condition that selects it. However, the positive "Cuándo" guidance (date, time-zone or calendar results needing exactness, DST, leap years) does not describe a use case for moon phase at all — it reads like boilerplate from a datetime tool, so an agent gets only half-usable routing guidance.

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