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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), so the bar is lower, and the description still adds real context: units are preserved, provisional flags are surfaced, 'stage is not navigable depth,' and sourceStatus separates retrieval from observation time using the oldest parameter. That is meaningful data-quality semantics beyond the structured fields.

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?

It is front-loaded with the core verb and payload, and most sentences carry weight about data quality. However, the units line ('ft, kt, s, F, mi') includes knot and mile units that are irrelevant to a river gauge tool, suggesting boilerplate, and sentences like the sourceStatus clause are terse to the point of being hard to parse.

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 no output schema, the description does its job on the return side by naming the measurements and source/freshness metadata, and annotations cover safety. The gap is the nested input object: an agent gets no help resolving riverId, which is the one thing it must supply.

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?

The single parameter (path.riverId) has 0% schema description coverage and is not mentioned anywhere in the description, so neither source documents what a riverId is or how to obtain one. The description compensates for the return payload but leaves the only input semantically empty.

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 names a specific verb ('Get') and resource (California river observations) and enumerates the payload concretely: USGS flow in cfs, gauge height in ft, water temperature in F, plus weather. It is clearly about one river's observational data, though it never distinguishes itself from near-neighbors like get_usgs_water, get_water_temperature, or list_california_rivers.

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 from the data listed, and no alternative tool is named for retrieving river data or for a single river vs. a list. It does supply one useful exclusion, 'No navigation or water-contact safety rating,' steering agents away from treating this as a safety source, but there is no positive when-to-use guidance.

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