swiss_health_search_datasets

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 doesn't mention that this is a read-only search, what the tool returns (list of datasets vs. data records), whether results are truncated, or any authentication requirements. For a search tool the safety profile is fairly safe, but the return format and pagination/limited-results behavior are undisclosed.

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 core purpose. The topic list is concise and useful. No filler or redundant text. Efficient and appropriately sized.

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?

For a search tool with no output schema, the description should clarify what the search returns, but it doesn't specify return format or whether it overlaps with the sibling swiss_health_get_dataset. The topic coverage is useful, but the tool would benefit from stating it returns dataset metadata (titles, descriptions) that can then be fetched by the sibling tool. Adequate but with a notable gap.

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 50%, with only 1 of 2 params documented in the schema. The description doesn't add parameter detail beyond the schema. The 'rows' parameter's meaning (number of results) is implicit but not explained. Query examples are provided in the schema, not the description, so the description adds marginal value over 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?

The description specifies a clear verb+resource: 'Search BAG datasets on opendata.swiss' and lists covered topics (infectious diseases, hospitalizations, mortality, vaccination rates). It differentiates from siblings reasonably well—there are similar search tools like swiss_opendata_search_datasets, swiss_energy_search_datasets, and swiss_statistics_search—but the BAG scoping does distinguish it. However, it doesn't explicitly contrast with sibling search tools.

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 implies usage context (searching Swiss health-related open data) but provides no explicit when/when-not guidance or named alternatives. The sibling tool swiss_health_get_dataset appears related (probably fetching a specific dataset after search), but no relationship is explained. Context is inferred rather than stated.

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