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

The description reveals the calculation formula, daily data refresh, and the optional history behavior with a Gold tier requirement. Since readOnlyHint=true is already provided, the description adds substantial extra context about data sources, update cadence, and tiered access, going well beyond the annotations.

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 packed with necessary information in just two sentences plus 'Updates: daily.' It front-loads the core function and output fields, with each clause earning its place. The structure is logical: what is returned, when to call it, and refresh cadence.

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 main return values, methodology, and use cases, and the schema covers the sole parameter. However, it is not fully explicit about whether the current snapshot covers all states or just top states, and it omits mention of the 'days' parameter in the main text (though the schema compensates). Overall, the tool is well documented but has minor ambiguity around snapshot scope.

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 only parameter, 'days', has a complete description in the schema (100% coverage), explaining it returns a historical series and the Gold tier requirement. The main description does not need to add parameter details to reach baseline; there is no additional semantic value provided beyond what the schema already states.

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 precisely states the tool returns a 0-100 climate loss pressure score by state, with detailed methodology (z-scored 90-day FEMA disaster-declaration frequency vs. 12.5-year baseline). It names specific output fields, clearly distinguishing it from generic siblings by tying it to FEMA data and state-level climate risk.

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 explicit trigger scenarios: 'Call when the user asks about flood or disaster loss trends, state-level climate risk, or FEMA declaration activity, or when timing underwriting throttles, reinsurance purchases, or catastrophe reserve decisions.' However, it does not name alternatives or state when not to use the tool, so it falls short of a 5.

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