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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive behavior, so the bar for added value is lower. The description still adds meaningful behavioral context: data freshness cadence (every 5-15 minutes), retention window (last 30 days), ordering (newest first), and the area-sweep behavior for lat/lon queries. This goes well beyond what the annotations 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?

Four sentences, all informative and none redundant. The description is front-loaded with the data type and authority, then covers invocation modes and ordering. The parenthetical station example is useful and compact.

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 real-time data tool, the description covers data source, units, freshness, retention, ordering, and both invocation modes. The only notable gap is that there is no output schema and the description does not detail the exact shape of returned readings, but it still provides enough context for an agent to call the tool correctly in the covered use cases.

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 input schema has 100% parameter coverage, so the baseline is 3 even without description-level parameter detail. The description does reinforce the station_number versus latitude/longitude alternative and gives a concrete station example, but the schema already documents those semantics thoroughly. No additional parameter meaning beyond the schema is introduced.

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 specific resource and data type: real-time water level and discharge readings from Water Survey of Canada gauges. It also differentiates itself from hydrometric_stations_near by explicitly directing users to pass a station number from that tool, framing this as the readings counterpart. The 'AUTHORITATIVE for how high is the Canadian river right now' phrasing makes the purpose unmistakable.

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?

The description gives concrete when-to-use guidance: current river height queries and flood watching in Canada. It also spells out two invocation modes, station_number versus latitude/longitude, and tells users where to obtain a valid station number. It does not explicitly state when not to use this tool versus related tools like current_observations, but the primary use cases are clear.

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