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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds meaningful non-safety context: the data provenance window, the definition of the metric, and the crucial methodological caveat that the returned figure is the band median rather than a prediction for a specific property.

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?

Two tightly packed sentences that front-load the metric and scope, then immediately qualify the optional branch and its interpretation limit. No filler; every clause carries either provenance or interpretive guidance.

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?

With no output schema, the description carries the return-value burden and does so by defining the ratio, the dollar-value variant, and the interpretation caveat. It stops short of describing anything about the depth bands themselves (e.g., how in-between depths resolve), a minor remaining gap.

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 baseline would be 3, but the description goes beyond the schema for building_value_usd by explaining its effect (returns ratio × value) and warns that the output remains a band median, not a home-specific estimate. The depth band and segment parameters are only echoed, not deepened.

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 names the exact metric returned (median damage ratio of FEMA actual cash value of damage over building value), the source (NFIP paid claims 2015-2024), and the breakdown dimensions (interior water depth band, single-family one-floor segment). An agent can tell precisely what this produces without opening the schema, and it is unambiguously distinct from the claims-by-county/state siblings.

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?

Usage is implied through the building_value_usd branch (ratio alone vs. ratio times value) and the caveat that the result is a band median, not a per-home estimate. However, it never states when to choose this tool over the sibling tools (e.g., nfip_claims_by_county, county_profile) or any precondition for use.

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