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

Annotations only cover the read-only/idempotent safety profile; the description adds genuinely new behavioral detail an agent needs: original elevation datum and units are preserved, provisional flags are retained, freshness is computed per measurement, the gauge source reports the oldest parameter so a fresh temperature cannot mask a stale level, and CDEC US/Pacific times are converted to UTC with unverified offsets marked unknown. These are non-obvious data-quality semantics that annotations cannot convey.

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?

The core output scope is front-loaded in the first sentence and each subsequent sentence adds a distinct constraint (datum/units, per-measurement freshness, timezone handling, scope limits). The units line at the end is compact. Slightly dense and jargon-heavy but nothing is filler.

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 read-only, no-output-schema tool the description does well on data semantics, units, and caveats. The significant gap is operational: nothing explains the required lakeId argument or how to obtain it, which matters given a nested path object and zero schema description coverage.

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?

There is one required nested parameter (path.lakeId) with 0% schema description coverage, and the description never mentions it: no explanation of the lake ID format, where IDs come from (e.g., list_california_lakes), or the nested path structure. With coverage this low the description must compensate and does not.

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 specifically what is returned: lake weather (wind/gusts in kt, air temperature in F) plus source-dated gauge measurements for California lakes. That is a concrete verb-equivalent plus resource and clearly separates it from land-weather siblings like get_wind or get_air_temperature. It never names a sibling alternative, so it stops short of a 5.

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?

"On-demand" implies a current-conditions fetch and the closing line "No wave forecast or launch opening guarantee" rules out some expectations, which is a partial exclusion. But there is no explicit when-to-use guidance, no mention of alternatives such as get_conditions, get_wind, or list_california_lakes, and no stated prerequisites.

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