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

Annotations already declare read-only, idempotent, open-world behavior, so the safety profile is covered. The description adds real operational context beyond that: it discloses the return contents (variable names, units, axes, time coverage, licence) plus the griddap/tabledap and depth-axis flags, which no annotation conveys. It stops short of pagination or error-response detail, so not a 5.

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?

Front-loaded with the return contents, then the imperative usage rule and its rationale, then the preconditions. Three compact sentences, each earning its place, no repetition of structured fields.

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 read-only lookup with no output schema, the description supplies the return-field inventory, the pre-query workflow position, and the two structural flags an agent needs (griddap/tabledap, depth axis). Nothing material for correct invocation is missing.

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% — the node enum is fully expanded with per-node dataset coverage and the default, and dataset_id points at its source tool. The description adds nothing about parameters beyond what the schema already says, so the baseline 3 applies.

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/scope: returns variable names, units, axes, time coverage and licence for ONE IOOS ERDDAP dataset. It also distinguishes itself from siblings by naming the pre-query role and the griddap/tabledap distinction, so an agent can separate it from ioos_erddap_search_datasets and ioos_erddap_griddap_point.

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?

Explicit and prescriptive: 'CALL THIS BEFORE QUERYING DATA', with the exact failure mode that motivates it (case-sensitive, operator-varying variable names producing a misleading 'station does not measure that' error). It also flags the depth-axis precondition for later queries, which is when-to-use guidance in effect.

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