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

Annotations already declare the tool as read-only, idempotent, and non-destructive, so the safety profile is covered. The description adds meaningful behavioral context: the dataset name, SDMX 2.1 format, sectoral breakdowns, unit options, and accepted country codes, plus the open license and no-auth requirement. It does not contradict annotations and supplements them with data specifics.

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?

The description is moderately sized but every sentence contributes: main purpose, data coverage, units, country codes, use case, and source/licensing. Information is front-loaded with the core action and resource. It avoids redundancy, though it could be slightly shorter without losing value.

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 4 parameters and output schema, the description covers the essential aspects: what data is retrieved, how to specify units and sectors, acceptable country codes, and typical use cases. It doesn't detail the return structure, but an output schema exists. The only minor omission is mention of the since_year parameter, but that is fully described in the schema. Overall, adequately 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?

Schema coverage is 100%, so all parameters have descriptions. The description adds examples for country codes (DE, SE, FI) and clarifies the unit meaning, but these are also documented in the schema. The sector codes and units are already explained in the schema, so the description adds marginal value beyond what the schema provides. 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 clearly states the tool retrieves annual Gross Domestic Expenditure on R&D (GERD) for EU/EEA countries from Eurostat, specifying the dataset (rd_e_gerdtot) and format (SDMX 2.1). It also enumerates the coverage (total and sectoral breakdowns) and units, distinguishing it from sibling Eurostat tools that focus on demographics, employment, energy, or environment.

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 description provides clear context for when to use the tool: 'Useful for innovation policy research and EU 3%-of-GDP R&D target monitoring.' While it doesn't explicitly exclude alternatives, the clear domain specification implicitly differentiates it from other Eurostat data tools. The 'no auth required' and source/license notes add practical guidance.

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