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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description goes well beyond them: explicit nulls when unavailable, source/freshness metadata, recorded-vs-reconstructed provenance, coverage/gaps, and a warning not to substitute wave/wind series for native chop. That is exactly the extra behavioral context the structured fields cannot supply.

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 purpose is good, but the body is dense and partly redundant – get_chop_history is named twice, and long imperative meta-warnings ('Never invent assistant-defined rough/calm thresholds...') read like prompt instructions rather than tool documentation. Several clauses could be tightened or dropped.

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, so the description usefully enumerates what comes back (timestamp, source status, explicit nulls, freshness metadata) and warns against silent substitutions. Given a forecast tool with an openWorld source, this is nearly complete, though param semantics and the choice-vs-sibling story remain thin.

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 0%, so the description must carry the load. It implies the two nested params ('verified spot', 'next hours') and gives units for the returned values, but never explains the spot ID format/pattern, the hours default of 24, or its 1–168 range. Marginal compensation for a 0% coverage 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?

Names a specific resource (chop / boat-ride conditions) and scope (a verified spot, next hours), and explicitly distinguishes itself from get_chop_history. The phrasing 'Boat ride and chop' is a bit idiosyncratic, but an agent can tell what it returns versus the history sibling without opening the 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?

Explicitly routes past-looking queries to get_chop_history with a verified spot ID, and states the temporal window ('over the next hours'). It does not say when NOT to use it versus the many other condition tools (get_waves, get_wind, get_conditions), so it stops short of full when/when-not guidance.

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