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

Annotations already declare readOnly/idempotent/openWorld, and the description adds real context beyond them: a 12-hour hourly horizon, the physical rule of thumb being modeled, coverage of 35 inlets, and what the answer says (rough now, easing, or turning rough). It stops short of noting data freshness or update cadence.

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 core question and 12-hour horizon are front-loaded, and the final sentence usefully summarizes inputs. The enumerated list of inlets is somewhat decorative but does evidence coverage, so it earns partial keep.

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 explaining returns and does so ('rough now, when it eases, when it turns rough later'). Inputs, coverage, and horizon are complete; only details like data source/freshness are absent, which is minor for this read-only forecast.

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 coverage is 100%, so lat/lon/name are already documented and the description's 'position... or an inlet name' largely restates them. 'For the nearest ones' adds a small point about proximity-based retrieval, but the schema could have carried that itself; baseline 3 is appropriate.

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 opening question plus 'worked out hour by hour for the next 12 hours' and 'Says if it's rough now, when it eases...' define a specific resource (Florida inlet/pass sea-state forecast) and verb (forecast/advise). It never names a sibling alternative, so it is clear but lacks explicit differentiation from tools like marine_forecast or sandbars.

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?

'Give a position for the nearest ones, or an inlet name' implies how to query and the two input modes, and the 'stacking up' framing implies when it is useful. There is no when-not guidance and no reference to competing tools, leaving usage inferred rather than stated.

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