Observaciones horarias de INUMET, por día local

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

Annotations already establish read-only/idempotent safety, and the description adds substantial non-obvious behavior: the source publishes in UTC but days are Uruguay local (UTC-3), an incomplete day returns null rather than a partial total, and the query window is capped at 400 days. The null-instead-of-partial rule in particular prevents an agent from silently producing wrong aggregates.

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?

Front-loaded with source, granularity and station list, then moves in a single step to mode semantics and constraints. Dense without redundancy; every sentence (timezone, null rule, aggregation rule) carries operational weight.

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, yet the description still sketches both return shapes (coverage metrics; per-day values), which is appropriate for a tool with two modes. Minor omissions for a tool this complex: no units (°C, mm), no behavior when `hasta` precedes `desde`, and no statement of what an empty `estacion` implies beyond the coverage-mode hint.

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 0%, so the description must carry the load, and it does: date format AAAA-MM-DD, the 400-day ceiling on desde/hasta, the mandatory nature of `agregacion`, and the variable-to-aggregation mapping. Gaps remain on the meaning of `promedio` across variables, the empty-string defaults for `estacion`/`desde`/`hasta`/`agregacion`, and how free-text station names map to the seven listed stations.

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 the specific resource (hourly INUMET weather observations aggregated to local days) and enumerates the seven stations covered, so the agent knows the data source and geographic scope. It does not, however, contrast itself with nearby siblings like `clima`, `nivel_rio`, or `estaciones_cercanas`, so the boundary of what this tool is *for* versus those is left to inference.

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?

Explicitly describes two invocation modes: passing only `variable` returns per-station coverage, while adding `estacion`, `desde`, `hasta` and `agregacion` returns per-day values. It even routes the agent to the correct aggregation per variable (max/min for temperature, suma for rain). It stops short of naming when to prefer a sibling tool instead.

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