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

Annotations already cover read-only, idempotent, non-destructive and open-world behavior, and the description adds substantial context on top: the upstream source (MET Norway Oceanforecast 2.0), that values are model output at the nearest model sea point rather than a buoy measurement, and that land or out-of-area points return empty results. It even discloses a cost of 1 credit, which is not captured anywhere in the structured fields.

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?

Information is front-loaded: purpose and coverage first, then data source and caveats, then coordinate prerequisites and cost. It is a single dense paragraph with parenthetical asides, which is efficient but slightly cluttered; the cost note and source note could be trimmed or split without losing meaning.

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?

There is no output schema, and the description compensates by describing what comes back (current value, 24-hour range, hourly series). For a two-parameter read-only lookup, the source, coverage limits, prerequisite tooling and cost disclosure leave nothing material an agent needs before calling it.

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 the two parameters are already documented as decimal-degree lat/lon, making 3 the baseline. The description earns above baseline by explaining how to obtain those coordinates (geocode or postcode_lookup) and by reinforcing that the point must actually be sea, which is the main way a caller gets a useless result.

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+resource ('Sea surface temperature forecast') plus scope: a coastal or offshore point in northern European waters, including UK coasts. It also enumerates the returned quantities (temperature now, 24-hour range, hourly values), so an agent knows exactly what this tool produces versus generic weather or marine 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?

Gives clear when-to-use framing via the intended audience (open-water swimmers, surfers, divers, anglers) and explicit prerequisites: obtain lat/lon from geocode or postcode_lookup first for UK place names or postcodes. It also states a failure condition (land points or outside the model area return no rows). The only gap is that it does not name marine_forecast or weather as the alternatives for wave or general conditions.

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