search_data_products

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

No annotations are provided, so the description carries the burden of behavioral disclosure. The description identifies it as a read/search operation through the phrasing, which is good. However, it doesn't disclose what the results structure looks like, whether search supports partial/prefix matching, or any pagination behavior beyond the 'limit' parameter. Given that a search tool is implicitly a read operation, this is adequate but not rich.

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 front-loaded with a single clear purpose sentence and analogies, then provides a lean Args block. The Args list is compressed but each line shows the parameter name and an example, which is efficient. The only minor critique is the 'certified_only' and 'limit' entries lack examples (though 'limit' is self-evident and 'certified_only' boolean is self-explanatory) — otherwise every sentence earns its place.

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 5 parameters (all optional), no annotations, and an output schema present, the description covers the key elements: parameter semantics with concrete examples, the purpose analogy, and implicit read-only behavior. The output schema handles return-value documentation. Given the tool's moderate complexity and that all parameters are optional with defaults, the description is reasonably complete. It could note whether keyword matching is fuzzy/exact, but this is not a critical 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 description coverage is 0%, so the description must compensate for all 5 parameters. The description provides a one-line explanation for each parameter with concrete examples ('Kundenhistorie Kündigungen' for query, 'DACH' for region, 'sales'/'marketing' for domain). The examples meaningfully enhance the bare schema by showing expected value formats and demonstrating that enum values for domain are not enforced but typical. This substantially compensates for the 0% schema coverage.

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 uses a specific verb ('durchsuchen'/search) plus a concrete resource ('Datenkatalog'/'data catalog') with an apt analogy to an internal marketplace product search. It clearly distinguishes the search function from siblings like search_glossary (different catalog being searched) and get_data_product (which retrieves a specific product).

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 frames this as searching a data catalog 'like a product search in the internal marketplace', which gives clear context for when to use it. The analogy to marketplace search helps the agent understand it's a broad discovery tool. However, it doesn't explicitly state when NOT to use it versus get_data_product (for a specific known product) or search_glossary (for glossary terms), though these distinctions are reasonably implied.

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