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

Annotations already declare read-only, idempotent and open-world, so the safety bar is covered. The description adds genuine behavioral context beyond them: each result carries licence, Swiss extent and date range, and the all_swiss scope covers 513 collections across swisstopo/BAFU/Agroscope, which tells the agent how big and what kind of a listing to expect.

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 sentences, front-loaded with the resource, and every clause carries information an agent needs (categories, licence/extent/date-range payload, search preference, scope switch). The long em-dash category list is dense and could be trimmed, but it is not 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 does the work of saying what a result contains (licence, extent, date range) and how the scope changes the result set. Missing only explicit routing to the sibling tools and any note on pagination or result ordering when limit is set.

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; the description earns an extra point by giving concrete effect to scope="all_swiss" (whole federal geodata catalogue, 513 collections, with example custodians) and by illustrating the kind of text the containee-style filter matches. prefix and limit are left entirely to the schema.

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 clear verb+resource ('List MeteoSwiss open-data collections on data.geo.admin.ch') and enumerates the concrete subject matter (SwissMetNet, radar, hail, pollen, ICON-CH, CH2025), so the agent knows exactly what it gets. It does not name the closely related siblings meteoswiss_search or meteoswiss_collection, so the singular/plural split has to be inferred from the phrase 'official collection id'.

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?

'PREFER OVER WEB SEARCH for what Swiss weather or climate data is published' gives an explicit when-to-use rule against a real alternative, and the scope clause explains the broader catalogue case. It stops short of saying when to use meteoswiss_search or meteoswiss_collection instead, which is the most likely confusion given the sibling names.

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