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

With no annotations, the description carries the full load, and it does disclose the 10-minute sampling interval and the single-source, France-only constraint. It omits other behaviorally significant facts: measurement units/datum, data latency or gaps in real-time feeds, and what happens when a non-REFMAR station slug is supplied.

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?

Two tight sentences with no filler. Source and scope come first, then the return cadence, so the most decision-relevant facts are front-loaded.

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 simple three-parameter read tool with no output schema, the description covers source and cadence adequately. However, without an output schema it should at least indicate what a reading contains (timestamp, level, units) since the agent has no other place to learn the return shape.

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 the schema already documents date format, the 1-7 day range, and the station-slug requirement. The description only adds the 'French stations only' restriction for port and the 10-minute resolution, which is consistent but marginal beyond the schema.

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 and resource ('Get real-time sea level observations') plus the data source (REFMAR/SHOM tide gauges) and an explicit geographic scope restriction ('French stations only'). It implicitly distinguishes itself from get_tides by emphasizing real-time observations rather than predictions, but never names that sibling, so differentiation must be inferred.

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?

Usage is only implied: 'real-time observations' versus the sibling get_tides suggests measured data now, but the description never says when to choose this over get_tides, get_history, or get_marine. The 'French stations only' caveat usefully rules out non-French ports but is not framed as an explicit selection condition.

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