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

Annotations already indicate readOnly, idempotent, openWorld, and non-destructive. The description adds valuable context: 'No auth — USGS public domain, updated every 15 minutes.' This goes beyond annotations by disclosing authentication requirements, data update frequency, and the public-domain nature, which are essential for an agent to set expectations.

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 dense but well-organized: it opens with the core action and output, then adds use cases, parameter details, and operational notes. Every sentence contributes value, and the most critical information (scope, real-time, basin) appears first. Slightly long but not bloated.

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?

The tool is well-covered: purpose, output, typical site count, use cases, parameter guidance, auth, update frequency, and units are all present. An output schema exists, so return structure is defined. Nothing critical is missing for an agent to decide and invoke this tool correctly.

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%, but the description enriches both parameters. For huc_code, it explains what a HUC-8 is, provides a concrete example ('02070008' for the Potomac), and advises using 8-digit HUCs. For period, it gives the ISO 8601 format, a default, and a behavioral caveat about response time for longer periods. This exceeds the baseline for full schema coverage.

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 explicitly states the verb and resource: 'Get real-time streamflow readings for all active USGS gauge stations within a HUC-8 watershed basin.' It specifies the output (discharge in ft3/s per station) and typical scale (5–40 sites), clearly distinguishing it from sibling tools like annual_stats, daily_values, and site_info by focusing on basin-wide real-time data.

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 provides clear use cases ('Ideal for watershed-scale flood monitoring, drought assessment, and basin hydrology surveys') and emphasizes the basin-wide, single-call nature. While it does not explicitly name alternative tools or state when not to use it, the scope and real-time framing effectively guide selection among related NWIS streamflow tools.

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