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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains the data source (NBCN), the resolutions available (daily, monthly, yearly), the number and type of stations, and the accepted input formats. It falls short of mentioning potential error behavior, date range limitations (beyond 'going back decades'), or any data adjustments (e.g., 'homogeneous' implies homogenization but isn't explained). Overall, it is transparent about what the tool returns and how to invoke it.

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 moderately long but well-organized: it opens with a direct statement of purpose, then details network and resolution, provides use cases, and ends with input formats. Every sentence earns its place, and the structure helps the agent quickly grasp the tool's scope. It is slightly verbose in the station count detail, but that is useful context for selecting the tool.

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?

Given the tool's complexity (6 parameters, nested coordinates object, output schema), the description covers the essential aspects: data content, geographic scope, resolution options, station types, and input alternatives. It does not explain the output structure, but an output schema exists to handle that. It also omits specific date range limits or station list details, but the sibling 'meteoswissStations' likely covers that. Overall, it is sufficiently complete for an agent to understand when and how to invoke 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?

The input schema already describes all parameters with 100% coverage, giving a baseline of 3. The description adds value beyond the schema by providing concrete examples of valid station abbreviations ('SMA', 'BAS'), clarifying the meaning of 'homogeneous' (though not fully), summarizing resolution differences (daily temp min/max/mean, monthly full summary, yearly annual summary), and illustrating the precedence of coordinates over station. This extra semantic context justifies a score above baseline.

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 clearly states the tool's function: 'Get homogeneous climate measurement series from Switzerland's National Basic Climatic Network (NBCN)' and enumerates the types of data returned (temperature, precipitation, sunshine, radiation, wind, pressure, climate indicators). It is specific about the verb (Get), resource (climate series), and scope (Switzerland, NBCN), and it effectively distinguishes itself from sibling tools by focusing on historical climate data rather than current weather or forecasts.

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 clear usage context through example use cases ('What are typical January temperatures in Zurich?') and input options (station names, abbreviations, coordinates). It does not explicitly state when not to use the tool or name alternative tools, but the context strongly implies this for historical climate queries versus current conditions. A clear exclusion statement would make it a 5.

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