Dataset Discovery

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

With no annotations, the description bears full responsibility for behavior. It implies a read-only search ("find") but doesn't state return format, pagination, side effects, or any constraints. Agents cannot predict what the tool returns or how filters combine.

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 sentence, front-loaded with the core action. It is concise, but its brevity sacrifices the clarity needed for a tool with six unlabeled parameters. No wasted words, yet it under-delivers on useful guidance.

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?

Missing critical context for a search tool: no mention of default behavior, result limits, output format, or interaction with sibling tools like `download_dataset`. The description leaves agents guessing about pagination, filtering semantics, and whether multiple criteria are ANDed or ORed.

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 has 0% coverageainerneither descriptions nor enums, so the description must compensate. It lists most parameters (task, modality, annotation, object_class, license) but omits `limit` and the phrase "access needs" doesn't map to any parameter. No value formats or examples are given, leaving the agent to guess valid inputs.

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 clear verb (find) and resource (datasets) and enumerates filtering dimensions (task, modality, object class, annotation type, license, access). It distinguishes itself from sibling tools like list_skills and get_dataset_download_plan, though it doesn't explicitly contrast with run_dataset_discovery, which might overlap.

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 guidance on when to use this tool versus alternatives. The description only lists filter criteria but does not mention when to prefer find_datasets over search_resources or run_dataset_discovery, nor any exclusions or prerequisites.

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