forecast_cloud_cover

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

With no annotations, the description carries the full burden and discloses a meaningful caveat: the total is an estimate assuming independent layers because MeteoSwiss publishes layers separately. It also explains why all three layers are returned (distinguishing low fog from thin high cloud) and what the response includes (place, forecast point, valid time, model run). It does not mention rate limits, units caveats beyond percent, or failure behavior for out-of-range times.

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 the purpose, then a caveat paragraph, then a routing sentence, then args/returns/examples. Every section is short and the examples are concrete rather than decorative. The literal Args/Returns block formatting is slightly heavier than prose would be, but no sentence is wasted.

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?

No output schema exists, so the Returns section does the work of describing the shape (total plus low/medium/high percentages, place, forecast point, valid time, model run) and does it adequately. Together with the estimate caveat and the time-window constraint, an agent has enough to call it correctly. Minor gaps are the 'near' disambiguation flow and any failure mode for unavailable times.

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 33%: only 'near' is documented in the schema, while 'location' and 'when' are bare. The description compensates by defining location as a town, village, city district, lake or peak with examples, and by specifying the exact time format (full hour, ISO 8601 without offset, today to 8 days ahead). That is real added meaning, but the overlap/ambiguity handling for duplicate place names is left entirely to the schema and never reinforced in the description.

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: 'Get how cloudy it is at a place at a specific time.' The second paragraph distinguishes it from plain-language cloud reporting and names the three cloud layers it returns, so an agent can tell it apart from forecast_hourly. It does not explicitly contrast against forecast_daily or forecast_rain, but the numeric cloud-cover scope 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?

Explicitly routes the plain-word case to forecast_hourly ('when a number is not needed'), giving a clear when-not condition and a named alternative. It also states the time window ('today or up to 8 days ahead'), which sets a usable boundary. No guidance on when to prefer the layer breakdown vs a total-only read, but the essentials are present.

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