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

The annotations already cover read-only, open-world, idempotent, and non-destructive behavior, and the description adds useful context: 'Returns one measurement per day (midnight UTC)', 'Coverage: 1,500+ active US streamflow stations, records from 1900s to present', and 'No auth — USGS public domain, unlimited calls.' However, 'over any date range' overstates the schema's stated 1-year maximum range, so full accuracy is not achieved.

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 description is compact and front-loaded: main action, return behavior, optional parameters, use cases, coverage, and auth are covered in about five sentences. There is no filler or redundant restating of the schema.

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 values tool with an output schema, the description covers the essential operational facts: what data is returned, units, station lookup, coverage, auth, and suitable use cases. It would be stronger with an explicit statement of the 1-year range cap and the correct sibling name, though the schema already documents the range cap.

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 coverage is 100%, with detailed descriptions for site_no, start_date, end_date, and parameter_cd, including formats, defaults, and enum meanings with units. The description largely repeats the parameter_cd options and station lookup hint rather than adding meaning beyond the schema, so the baseline 3 is appropriate.

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 opens with a specific verb+resource statement: 'Get historical daily mean streamflow (discharge) values for a USGS gauge station over any date range.' It also specifies the return cadence, units, and optional parameters, making it easy to distinguish from the real-time and annual-statistics siblings even without naming them.

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?

It gives concrete routing guidance ('Use water.sites to look up station numbers by state or bounding box') and lists intended use cases such as trend analysis, drought monitoring, flood season review, and hydrology research. It does not explicitly exclude alternatives like real-time or annual-statistics tools, so it stops short of a 5; also, the referenced 'water.sites' appears in the sibling list as 'water.usgs.sites'.

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