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

Annotations already cover safety (read-only, idempotent), and the description adds behavioral details: the search scope (~10,000), the specific return fields (codes, titles, dates, time range), and the fact that it does not return the actual numbers, requiring a follow-up get_dataset call. No contradictions.

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 concise sentences plus an example. The description is front-loaded with purpose and resource, and every sentence provides useful information without filler.

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?

Given the low complexity (single parameter) and the presence of output schema and annotations, the description covers purpose, scope, return values, and follow-up action. The mention of scale (~10,000) and the example add sufficient context.

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 the parameter already described ('Search keyword, e.g. ...'). The description adds an example invocation but does not significantly enhance the parameter explanation beyond the schema's examples section. Baseline 3 is appropriate.

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 specific verb 'Search' and identifies the exact resource ('full Eurostat table of contents ~10,000 datasets') with clear output fields. It explicitly distinguishes from sibling get_dataset by directing users to pass returned codes there for numbers.

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?

It provides clear context for when to use this tool: to find datasets by keyword when you need codes and metadata. The instruction to 'pass a returned code to get_dataset for the numbers' implicitly sets boundaries, though it does not explicitly mention alternatives like list_datasets or when not to use.

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