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

With no annotations, the description carries the full burden, and it does disclose the return payload (name, slug, platforms, modalities, episode count, hours, license, access type, URL), which is genuinely useful. It says nothing about result caps, pagination, sort order, or whether multiple filters combine with AND or OR — the operational facts an agent needs to avoid misreading results.

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, both earning their place: the first front-loads capability and scope, the second front-loads the return shape. No filler or restatement of the tool 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?

All six parameters are optional and documented in the schema, and the return fields are enumerated in the description, so an agent can call this correctly. The remaining gap is behavior on unfiltered calls (full 540+ dump? capped?) and filter combination logic, which matter for a search tool with no output schema to fall back on.

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% and each parameter has a concrete example, so the baseline is 3. The description echoes four of the six parameters but adds no semantics beyond the schema and omits the `query` and `category` filters, so it neither compensates nor detracts.

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?

States a specific verb (search) plus a precisely scoped resource (Geppetto's directory of 540+ robot training datasets) and enumerates the filter dimensions. Clearly distinguished from siblings like search_robots, search_suppliers, and get_dataset by domain and by list-vs-single semantics.

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?

The filter vocabulary in the first sentence tells an agent when this tool applies (narrowing by platform, modality, license, or commercial-use), which is real usage context. It stops short of naming alternatives or exclusions — e.g., that get_dataset should be used when a specific dataset is already known.

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