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

No annotations are present, so the description carries the full burden for behavioral disclosure. The verb 'Return' reasonably implies a read-only operation with no side effects, but the description does not describe metric semantics, units, or behavior for invalid or missing datasets. It is minimally adequate but thin.

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 compact and front-loaded with the core behavior ('Return a per-dataset metric'), followed by a terse, well-formatted argument list. There is no filler or redundant restatement of the tool name.

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 simple two-parameter getter with an output schema, the description covers both parameters and their allowed values, and the output schema handles return shape. The main gap is that it does not explain what each metric means or when to choose this tool over portal-level metrics, but the invocation path is clear.

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 description coverage is 0%, so the description must compensate. It fully does: dsid is explained with a format (dNNNNNN) and a concrete example, and metric is given an explicit list of allowed values. This adds essential meaning absent from 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 states a clear verb and resource: 'Return a per-dataset metric.' It also enumerates the metric values, which makes the operation concrete. It does not explicitly contrast with the sibling get_portal_metrics, but 'per-dataset' provides enough differentiation.

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?

There is no guidance about when to use this tool versus alternatives such as get_portal_metrics or describe_dataset. The description implies it should be used to fetch dataset metrics, but it does not state exclusions, prerequisites, or a preferred alternative.

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