search_catalog

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

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds the server-side capping of limit due to upstream ignoring paging, and the limitation that some type filters yield zero results despite existence. This adds valuable behavioral context beyond annotations, though could mention rate limits or error handling.

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 well-structured with a main paragraph, a limitation note, and parameter list. It is informative but slightly verbose; some sentences could be tightened without loss of clarity.

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, sibling tools) and presence of output schema, the description covers all essential aspects: purpose, when to use, parameter semantics, known limitations, and alternatives. No gaps in guidance for effective invocation.

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?

Despite 0% schema description coverage, the description provides detailed explanations for all 6 parameters in the Args section, including query free-text, language options, types (with known limitation), themes, publishers, and limit behavior. This fully compensates for the schema's lack of descriptions.

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 it 'searches Switzerland's national metadata catalogue for data resources' and describes it as the primary entry point to find who publishes data on a topic. It lists returned fields (titles, publishers, themes, permalinks) and distinguishes from sibling tools like list_concepts and list_data_services.

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 says 'use this to find out *who* publishes data on a topic before looking for a specific dataset.' Provides a known limitation that types other than 'Dataset' may return zero results and directs to alternative tools (list_concepts, list_data_services). Also warns against empty query returning full index.

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