Search datasets

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

Annotations already declare readOnly/openWorld/idempotent, so the safety profile is covered. The description earns credit by disclosing a non-obvious cost model ('5-15 credits by rows returned'), which is nowhere in the structured fields and directly affects how an agent should size its limit.

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?

A single dense sentence that front-loads the resource, then filters, then cost. Nothing is padding, though the endpoint label '(GET /datasets)' is arguably redundant given the name.

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 6 optional params fully described in the schema and no output schema required, the core is covered. However, nothing addresses pagination behavior across offset/limit (relevant for a cost-per-row tool) or the shape/order of results, which is where completeness gaps remain.

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 100%, so sort direction, limits, and offset semantics are already fully documented in the schema. The description only restates three filter fields (category, author, license) at a high level, adding no syntax or default details beyond the schema — baseline 3.

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?

Names a specific verb+resource ('search datasets'), scopes the domain ('alignment and uncensoring datasets'), and cites the backing endpoint (GET /datasets). It does not explicitly contrast itself with the sibling get_dataset or list_delisted, so an agent must infer the search-vs-retrieve distinction.

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?

No when-to-use guidance and no named alternatives. The filter list implies the tool is for filtered browsing, but nothing tells the agent when to prefer this over get_dataset or search_models.

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