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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds only that this is a single-dataset metadata fetch; it says nothing about behavior on an unknown dataset_id, rate limits, or response shape beyond the field list.

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?

A single sentence with no filler, the resource and returned fields front-loaded, and the usage instruction placed at the end where it reads naturally.

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?

With no output schema, the description usefully enumerates the returned metadata. It stops short of covering failure or empty-result behavior for a bad dataset_id, which is the main remaining gap for a one-parameter lookup.

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?

Only one parameter and schema description coverage is 100%, with the schema itself noting dataset_id comes from search_datasets. The description reinforces the point by tying the call to learning column names, but adds no format or validation detail 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?

States a specific verb (get) and resource (metadata for one Occitanie Region Open Data dataset) and enumerates what is returned (fields/schema, themes, record count). This clearly separates it from siblings like query and search_datasets, which operate on data rather than metadata.

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?

Explicitly instructs 'call before query to learn the column names', giving the agent a clear sequencing rule relative to the query sibling. It does not state when-not to use it (e.g., for datasets already inspected) or mention search_datasets as the discovery alternative in the description itself, so it falls short of full 5.

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