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

Annotations already declare the safe-read profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint). The description adds real behavioral value beyond them: data provenance (median of the state agency model run), the expected-empty-result condition, and the non-authoritative disclaimer. It stops short of describing pagination or cadence of publication.

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 tight sentences: what it returns first, then the availability caveat, then the disclaimer. No filler, and each sentence carries distinct information.

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 an output schema present, return values need not be explained. The description covers the remaining agent-critical unknowns: provenance, that empty results are normal, and that the output is indicative rather than an official warning.

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% and both parameters are documented there, including the default 72 and the 240 cap. The description only echoes the horizon concept ('future points within the horizon') and adds no syntax or format detail, so the baseline 3 is appropriate.

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 states a precise verb and resource ('Newest published water-level forecast for a station') and pins down the exact quantity returned (median of the state agency model run, future points within the horizon). This lets an agent distinguish it from get_readings (current observations) and get_flood_situation without opening any 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 gives a clear applicability condition ('Only gauges whose state publishes numeric forecasts have one, so an empty result is normal') and a framing caveat ('Indicative, not an official warning'). It does not explicitly name a sibling alternative for the case where no forecast exists, but the when-it-applies guidance is strong.

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