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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior. The description adds value by specifying what metadata is returned (fields/schema, themes, record count), which is useful since there is no output schema.

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 a single, well-structured sentence that front-loads the core purpose. Every word contributes value without redundancy.

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?

The description succinctly covers what the tool returns (fields/schema, themes, record count), which is sufficient for a metadata tool with no output schema. It could mention that it does not return actual data, but the mention of 'metadata' implies this.

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 only parameter dataset_id is described in the schema as 'from search_datasets,' and the tool description reinforces that context. However, the description does not add new meaning beyond what the schema already provides, so it's adequate but not exceptional.

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 gets metadata for a Nantes Métropole Open Data dataset, specifying fields/schema, themes, and record count. It distinguishes from sibling tools like search_datasets and query by indicating this is a preliminary step to learn column names before querying.

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 says 'call before query to learn the column names,' providing clear guidance on when to use this tool. While it does not list alternatives, the context makes the usage intent obvious.

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