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

With no annotations, the description must carry behavioral disclosures. It does mention pricing per endpoint and notes that 'gauge' and 'supply-snapshot' are 'deterministic', but it omits critical operational details: it never states that the 'action' parameter is required to select an endpoint, nor does it explain response formats, data limitations (e.g., USGS/Hydrology coverage is US-only despite 'Coverage: Global'), or any access prerequisites. This leaves significant behavioral ambiguity.

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 uses a bullet-list structure for endpoints, which is helpful, but it is marred by a malformed opening sentence that cuts off ('global water stress, a') and an inaccurate endpoint count ('9 endpoints' vs. 11 listed). This structural inconsistency reduces clarity and undermines conciseness. The content could be trimmed and corrected.

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 description covers the breadth of endpoints but lacks depth. It does not explain that the 'action' parameter must be set to one of the listed endpoint names to invoke a specific capability, nor does it describe required parameters per endpoint, expected output data, or any examples. Given 11 sub-actions and no output schema, the description falls short of enabling correct invocation without additional inference.

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 already provides 100% parameter description coverage (e.g., 'site: USGS site number — e.g. 09380000...', 'focus: agriculture | municipal...'). The tool description adds no additional parameter-level semantics; it only repeats endpoint names. Thus, the baseline of 3 is appropriate since the schema handles parameter meaning.

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 clearly identifies the tool as a global water intelligence API with multiple endpoints, each with a brief explanation. It is distinct from sibling tools (e.g., climatepulse, marketpulse) by focusing on water data. However, the opening sentence claims '9 endpoints' while actually listing 11, which introduces confusion about the tool's scope.

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?

Each endpoint is listed with a clear description of what data it returns (e.g., 'groundwater levels (USGS)', 'drought status (US Drought Monitor)'), allowing an agent to infer which endpoint to select based on the user's need. It lacks explicit 'when not to use' guidance or mention of alternatives, but the context is sufficient for basic selection among the listed sub-actions.

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