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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), so the bar is lower, yet the description still adds real behavior: a default 24-hour position window, the rule that yachts with unpublished positions are never listed, and the fact that results are keyed to the source site yachtfinder.co. It does not mention rate limits or failure behavior for an unresolvable place name.

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?

Front-loaded with the core purpose in the first clause and the exceptions (default 24h window, unpublished positions) after. Three tight sentences with no filler, though each is long and the result-field enumeration is somewhat list-like inside prose.

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 annotations and an output schema present, the description is nearly complete: it explains the source, the freshness default, and the inclusion rule. It is slightly redundant in enumerating returned fields that the output schema already covers, and it does not address what happens when no place or coordinate is supplied despite zero required parameters.

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 only 43%, so the description needs to carry weight; it clarifies the place-vs-coordinates choice and the default recency window, but says nothing about status, limit, or radius defaults that remain thin in the schema. Partial compensation only, hence a mid score rather than a higher one.

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 gives a precise verb and resource ("List the yachts") and narrows it with an unmistakable criterion: AIS positions within a radius of a named harbour/anchorage or a lat/long pair. That geospatial scoping distinguishes it in practice from find_yachts and yacht_facts without the agent needing to open a schema.

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 states the selecting condition (named place OR coordinates) and provides concrete place-name examples ("Port Hercule", "Antibes", "Off Monaco"), which is clear usage context. It never names find_yachts as the alternative for non-proximity queries, nor states when not to use it, so it stops short of a full 5.

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