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

Annotations already declare the tool as read-only, idempotent, open-world, and non-destructive. The description adds the workflow context about checking server instructions and preferring query_dataset, but does not disclose additional behavioral details such as result ordering, matching logic, or that it searches across multiple portals. Given annotations cover safety, the description provides minimal extra behavioral insight, so a 3 is appropriate.

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 effectively front-load the core action ('Search datasets by free text') followed by a high-priority usage note. There is no wasted text; the IMPORTANT warning earns its place by preventing unnecessary searches.

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?

The tool has four parameters and no output schema, but the schema fully documents inputs. The description provides necessary workflow context about when to use this tool versus query_dataset, and the sibling list includes list_categories for category filtering. However, it does not state what the tool returns (e.g., a list of datasets with metadata), which would help an agent know what to expect from the response. Given the calibration example, a 4 is suitable.

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 100%, with each parameter having a descriptive comment including defaults, constraints, enums for portal, and examples for query and category. The description itself does not add parameter-level detail beyond the schema, so baseline 3 applies.

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 the specific verb 'Search' with resource 'datasets' and specifies 'free text' as the input modality. It explicitly distinguishes from query_dataset by stating to only use when you don't know which dataset you need, which sets it apart from 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?

Explicitly advises checking server instructions first and states that many common queries have a direct dataset_id better served by query_dataset. It gives a clear condition: 'Only use search_datasets when you don't know which dataset you need.' This is explicit when-to-use and when-not-to-use with a named alternative.

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