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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real value beyond that: the provenance of the numbers (ERA5 reanalysis, Météo-France sea temps, airport station) and the instruction to cite the returned URL, which is an operational requirement not encoded anywhere else.

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?

Two dense sentences with the dataset scope front-loaded, followed by the calling modes and the citation instruction. The field list is long but each item is substantive; nothing reads as filler.

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 must carry the return-value burden, and it does by enumerating the metrics and their sources, the time coverage, and the two response shapes. Minor gaps remain (units, whether waves are significant-height, how the URL is surfaced), but an agent has enough to call and interpret it.

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%, so the baseline is 3, and the description goes beyond the schema by specifying the default behavior (absent parameter = all-12-month overview) and the effect of supplying month (single month, more detail). That default-vs-explicit semantics is the one thing the schema cannot express.

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 resource (monthly climate normals for Phuket 2015–2025) and enumerates the exact datapoints returned — precipitation median/mean, rain days, air and sea temperature, waves, cloud cover — plus the underlying sources (ERA5, Météo-France, airport station). This clearly separates it from current-condition siblings like get_weather_now, get_observed_weather and get_sea_today.

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 explicitly defines the two calling modes: without the parameter it returns an overview of all 12 months, with month (1–12) it returns one month in detail. That is clear invocation guidance, but it never names the current-weather/sea siblings an agent should prefer for 'now' data, so the when-not is implied rather than stated.

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