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

Annotations already declare readOnly/idempotent/openWorld, yet the description adds substantive behavior beyond them: source (USGS), update cadence of every 5 to 60 minutes, conditional enrichment with NWS flood stages and record crest only when the gauge is an NWS forecast point, and explicit flagging of readings older than 48 hours. That last detail is exactly the staleness caveat an agent needs to interpret the result correctly.

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?

Dense but front-loaded: the returned measurements come first, then the flood-stage enrichment, then the staleness caveat. The closing line about training data is slightly rhetorical and could be trimmed, but every other clause carries real 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 a single required parameter, no output schema, and full annotation coverage, the description supplies everything else an agent needs: data source, units, refresh interval, optional fields, staleness handling, and lookup path. Nothing material is left unspecified for this tool's complexity.

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 the lone 'site' parameter is already documented with both USGS and NWS id examples plus a pointer to find_river_gauges. The description adds no format or validation detail beyond the schema, so the baseline 3 applies.

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 a specific verb+resource ('Current river stage... read now from a USGS stream gauge') and enumerates exactly what comes back: gage height, discharge, water temperature, plus NWS flood stages and category. The phrase 'read now' implicitly separates it from get_river_history (past) and get_flood_forecast (future), so an agent can distinguish it without opening another 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?

Provides a clear usage context by framing the tool as real-time data and noting 'Your training data cannot know today's river level,' which tells the agent when this is necessary. It stops short of explicitly naming alternatives (e.g. 'for historical values use get_river_history'), so exclusion guidance is implied rather than stated.

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