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

Annotations are absent, so the description carries the entire behavioral burden. It says the tool returns wave conditions and covers a fixed geographic region, but says nothing about whether this is a read-only operation, whether forecasts carry uncertainty/time horizons beyond the 1–48h hours parameter, data licensing, or units of the returned wave height (feet, meters). Without annotations there is no safety or mutational profile at all.

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?

Three lines, dense with signal; scope and coordinate system in the first sentence. No orphan phrases like 'this tool does' or 'see schema for details.'

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?

After adding annotations and a good parameter schema, the missing pieces are: no output schema (the agent doesn't know what response fields look like), no mention of data freshness or source attribution, no latitude/longitude-order gotcha, no error semantics. For a wave-forecast tool these aren't fatal, but the lack of any return value disclosure in the description is a real gap.

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_parameter_description_coverage is full: every parameter has a schema description (latitude, longitude, hours). The semantic says latitude/longitude are decimal degrees, hours has min/max/default. Description adds no mention of coordinate format (e.g. 'lat, lon' vs 'lon, lat') above the schema, so saw a small amount of redundancy, but the schema carries the weight.

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 ('Wave height, wave direction, and sea temperature') and a geographic scope ('Norwegian coast and nearby seas'). It does not explicitly name a sibling, but for a standalone forecast tool in this domain the core purpose is unambiguous.

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 implies use (forecasting along the Norwegian coast) but it names no alternative tool and gives no exclusion or when-not-to-use context. An agent could still call it to request a wave forecast anywhere on Earth and get a result that doesn't apply.

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