search_datasets

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

Even though annotations already mark readOnlyHint and openWorldHint, the description discloses that the tool is a stub that always returns an unsupported error (E6, E7). That is precisely the kind of behavior an agent cannot infer from annotations or schema. It fully signals the critical trap of calling this tool.

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: the first states the core purpose in a compact phrase, the second delivers the critical caveat. Every word earns its place and the most decision-relevant fact (unsupported) is prominent. This is appropriately sized for a stub tool.

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?

For a disabled tool, the description tells agents not to call it and what error to expect, which is sufficient for that purpose. However, it gives no hints about how to accomplish the intended search task otherwise, such as consulting list_sources or another tool. Given the six-parameter schema, a pointer to alternatives would have made it complete.

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?

The description only hints that 'query' is a text query and that 'source' identifies an archive/catalog; the other four parameters (cursor, assembly, organism, max_records) are entirely unexplained. With only 17% schema coverage, this leaves most parameter semantics to inference. The stub status mitigates the impact, but the description adds little to the schema.

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 names the action ('search'), the resource type ('studies or datasets'), and the input ('text query'), and narrows scope to 'one archive/catalog'. It does not explicitly contrast with sibling lookup tools, but its search intent is distinct. The appended 'not implemented' warning is clear, though it slightly complicates the stated purpose.

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 warning 'Not implemented in this build: returns error code unsupported' makes an explicit when-not to call the tool. However, it offers no alternative tools or conditions for using this search instead of the many sibling lookup/retrieval tools. Thus guidance is present but incomplete.

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