discover_datasets

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The phrase 'results are bounded' is vague—it hints at pagination or a limit but doesn't clarify what bounds apply, the default behavior, or whether the limit parameter controls it. It doesn't disclose the return format, ordering, or any side effects.

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 a single efficient sentence with minimal waste. It's front-loaded with the core purpose. However, it is over-terse; the brevity comes at the cost of needed content rather than trimming redundancy, which slightly undermines this as '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?

Despite having an output schema and only 2 optional parameters (simple tool), the description is under-specified. No annotations and 0% schema coverage mean it should carry substantial informational weight, but it doesn't. While the output schema covers return values, the tool's filtering/list semantics remain opaque.

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?

With 0% schema description coverage, the description must compensate for both parameters (limit and query), but it mentions neither. The agent doesn't learn what 'query' expects (catalogue identifier format?) or how 'limit' caps results. The schema gives only types and defaults with no meaning, and the description adds nothing about either parameter.

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+resource (find public water datasets) and a clear scoping mechanism (by catalogue identifier). It distinguishes from siblings like get_observations and find_stations by focusing on dataset discovery rather than data retrieval. However, it doesn't explicitly explain how it differs from describe_dataset, which could cause some ambiguity among dataset-focused siblings.

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?

There is no guidance on when to use this tool versus alternatives. No exclusions, no when-not-to-use, and no mention of alternatives like describe_dataset or find_stations. The description implies a search-or-listing use case but provides no explicit context for the agent to decide between this and sibling tools.

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