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

Annotations already declare readOnly, idempotent, non-destructive, open-world, so the safety profile is covered. The description adds genuinely non-obvious context: readings are provisional, the tool is not a flood warning or forecast, and it emits both PDF and CSV artifacts. Minor overlap in restating the 1-10 sites / 1-7 days limits keeps it from a 5.

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 front-loaded sentences: purpose first, then scope, then return artifacts, then limitations and routing. No filler, though the numeric range restatement overlaps with the schema and could be trimmed.

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 fetch tool with a fully covered schema and an output schema, everything an agent needs is present: trigger conditions, input bounds, artifact formats, data-provisional caveat, explicit non-capabilities, and the prerequisite sibling call. No meaningful gap remains.

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%, so all three parameters (site_ids, days, paper) are already fully documented including defaults and enums, which sets the baseline at 3. The description only repeats the cardinality limits ('1 to 10 USGS site numbers and 1 to 7 days') without adding format, validation, or failure semantics beyond the schema.

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 verb+resource pair ('current river flow (discharge) or gage height at USGS stream gauges') and enumerates the exact outputs (trend, historical comparison, printable condition sheet, PDF+CSV). It also names the sibling it is not ('use find_river_gauges first when the site number is unknown'), so an agent can route between the two without opening a 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?

The opening 'Use this when the user wants...' clause gives positive trigger conditions, and the closing sentences give explicit exclusions ('Does not forecast and is not a flood warning') plus the alternative tool to call when the site number is unknown. Both when-to-use and when-not-to-use are covered.

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