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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds meaningful behavioral context beyond that: it discloses that the tool surfaces griddap vs tabledap format, alerts the agent to a depth axis requirement, and warns about the failure mode of case-insensitive variable names. This enriches the agent's expectation without contradicting any annotation.

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 but information-dense: the output scope is front-loaded, followed by a strong usage directive with a concrete example, then two additional output features. Every sentence contributes. The only slight inefficiency is the parenthetical error example, which is illustrative rather than wasted, so it still earns a 4 rather than a 5.

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 metadata-looking tool with only two parameters, no output schema, and simple annotations, the description covers the essentials: what is returned, why it should be called before data queries, and the key caveats that affect downstream tool choices (griddap vs tabledap, depth axis, variable case sensitivity). An agent can select and invoke it correctly without additional information. A brief note on the response structure would have pushed it to a 5.

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 100%, with both dataset_id and node already fully documented in the input schema, including an enum for node. The description adds no parameter-specific semantics beyond what the schema provides — its value-add is about output content and usage timing, not parameter meaning. Baseline 3 is appropriate when the schema does the heavy lifting.

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 what the tool does: it returns variable names, units, axes, time coverage, and licence for one CoastWatch ERDDAP dataset. It also distinguishes itself from data-query tools by mentioning it tells you whether the dataset is griddap or tabledap, implying it is a metadata/preflight step rather than a data retrieval tool. However, it never names the sibling data tools explicitly, so it falls just short of the clear sibling differentiation that earns a 5.

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 gives explicit when-to-use guidance: 'CALL THIS BEFORE QUERYING DATA' and explains why with a concrete consequence (case-sensitive ERDDAP variables produce confusing errors). This strongly implies the alternative is one of the data query tools. It lacks an explicit 'do not use when...' statement and doesn't name the alternatives, but the directive is unambiguous and actionable.

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