get_structure

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

There are no annotations, so the description bears full responsibility. It discloses the key behavioral trait that codelists are truncated (important for agent expectations) and mentions the ellipsis indicator. It doesn't state return format or error behavior, but for a simple structure tool with an output schema, this is acceptable coverage. No contradiction with any annotations since none exist.

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 extremely concise: two short sentences plus a conditional instruction. Every sentence earns its place: the first defines purpose, the second provides usage order and alternative routing. No fluff or repetition.

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 tool with one parameter, an output schema, and explicit sibling references, the description is quite complete. It covers purpose, usage order, and truncation behavior. Minor gaps: doesn't explain what 'structure' exactly includes (only mentions dimensions and codes), but that's sufficient. The output schema likely provides return details. This nearly fully equips the agent.

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 0%, so the description must compensate. It does: 'dataset' is implicitly the dataset identifier, and the description explains that the tool returns dimensions/codes of that dataset. It also explains behavior around truncation. It doesn't specify the format of the dataset parameter, but the schema already declares it as a string. Overall, the description provides enough meaning beyond 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 clearly states the tool returns the dimensions and codes of a dataset, with a specific verb ('get') and resource ('structure'). It also distinguishes itself from siblings by noting that codelists are truncated and that list_codes should be used for full exploration. This effectively differentiates it from query_data and list_codes.

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 explicitly instructs to call this tool before query_data, establishing a clear usage order. It also provides a conditional rule: if a dimension shows '… et N autres', use list_codes to browse it. This directly tells the agent when to use alternatives, which is exactly what this dimension requires.

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