open_data_search

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

Far beyond the annotations, the description discloses the result cap (10 datasets), that no source files are downloaded, that no API key is required, that results are sandbox-simulated dummy data, that metadata is untrusted and must not be treated as instructions, and that licensing/reuse review always applies. These are genuine behavioral traits an agent could not infer from readOnlyHint=false and openWorldHint=true alone.

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 purpose and limits are front-loaded and the return-field list is useful, but there is repeated defensive boilerplate ('SANDBOX ... returns dummy data' / 'Sandbox results are simulated'; 'payment buys normalized search access' / 'never your wallet'). Trimming the duplicated sandbox and payment sentences would strengthen it.

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 listing return fields (source, query, simulated, retrieved_at, total_matches, datasets, truncated, coverage), which is exactly what an agent needs to interpret results. Parameter documentation is adequate given the enum and schema hints, though the source distinction could be one line clearer.

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%; the query parameter is already documented in the schema, but the description adds meaning the enum alone does not: 'govdata' maps to Germany and 'open.bydata' to Bavaria, which helps the agent pick a source. It also reinforces that the query searches catalog metadata rather than downloaded data.

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 states a specific verb and resource ('Find public dataset catalog entries in GovData (Germany) or open.bydata (Bavaria)') and enumerates the fields returned, so an agent knows exactly what the tool yields. It stops short of naming or contrasting sibling tools such as regional_data, leaving a small ambiguity about which catalog/regional tool to prefer.

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?

It gives partial usage context: 'One catalog GET, up to 10 datasets; never downloads the actual source files' and 'No API key needed' tell the agent about cost and limits. However, there is no explicit when-to-use/when-not guidance and no named alternative for overlapping needs like regional_data or website_content.

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