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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered. The description adds genuinely new behavior: the MET Norway Oceanforecast 2.0 source, nearest-model-sea-point resolution, empty results for land or out-of-area points, and a 1-credit cost. It does not describe pagination or row shape, but with no output schema that is a minor gap.

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 definition is front-loaded with the resource and variables, then layers scope, use cases, source, caveats, and prerequisites. It is dense but nearly every clause carries information; the parenthetical cost note is slightly tacked on but still useful.

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 carries the burden of describing returns, and it does so by listing the hourly variables and the source model. Combined with the geographic bounds and the empty-result caveat, an agent has enough to call it correctly; only the exact response shape and timezone of the hourly series are unstated.

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%, so lat, lon, and hours are already documented with types and ranges. The description adds only the constraint that the coordinates must be a sea point and that coordinates may need to be obtained elsewhere first. That is useful but marginal beyond the schema, 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?

The description names a specific resource (sea-state forecast) and enumerates the exact variables returned: significant wave height and direction, surface current speed and direction, and sea temperature. It also bounds the geography (Norwegian Sea, North Sea, Skagerrak, Barents Sea, NE Atlantic, UK coastal waters), so an agent can distinguish it from generic weather or wind_forecast siblings.

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?

It gives concrete use cases (sailing, kayaking, fishing trips, coastal swims), an explicit exclusion (not a navigational or safety product), and a failure condition (land points or out-of-area return no rows). It also routes the agent to geocode or postcode_lookup for coordinates. It stops short of naming sibling alternatives such as weather, wind_forecast, or sea_temperature, which keeps it from a 5.

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