get_metadata

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

No annotations are provided, so the description carries the full burden. It discloses that the tool returns download hrefs, dimension descriptions, release date, and usage notes, but does not explicitly state that it is read-only or discuss prerequisites, rate limits, or error conditions. Given the absence of annotations, this is moderately transparent but could be more thorough.

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 three sentences, front-loading the core purpose and proceeding to list contents and usage guidance. Every sentence contributes value, and there is no fluff. It is concise and well-structured.

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 that the tool has three required parameters and no schema descriptions, the description covers the what but not the how (parameter details) or edge cases (e.g., error handling). An output schema exists but is not shown, so the description's list of return items is helpful but incomplete for full understanding. The context of sibling tools suggests this is a metadata retrieval tool, and the description adequately distinguishes it from per-observation queries but not from other metadata-related tools.

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 input schema has three parameters (dataset_id, edition, version) with no descriptions. The description does not elaborate on them beyond implicating a 'dataset version', so it adds minimal meaning beyond the schema property names. With 0% schema description coverage, the agent may need to infer parameter formats or constraints.

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 ('get') and resource ('full metadata for a dataset version'), listing specific contents like download hrefs and dimension descriptions. It differentiates from sibling tools like get_observations by indicating this is for bulk download.

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 states when to use this tool ('when bulk download is more sensible than per-observation queries'), which contrasts with get_observations. However, it does not mention other siblings like get_dataset or get_dimensions, leaving some ambiguity.

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