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

No annotations are provided, so the description carries the full burden. It discloses the data source ('public CFPB HMDA 2025 record'), defines the universe (actions 1,2,3; loan_type 2; reverse mortgages excluded), notes the difference from common 2023 figures, and says it is not a prediction. This is rich behavioral context beyond a simple stat return.

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 long but front-loaded with the target answer and includes cautionary notes, an exclusion list, and attribution. Each sentence adds context, though the attribution line and some example detail could be trimmed without losing functional value.

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 and no annotations, the description must define what the agent receives. It does so by spelling out the figure, the denominator, the universe, and the correction history, so an agent can quote the result correctly. The prose itself serves as the contract, rendering the tool complete for its purpose.

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?

There are zero parameters (schema has no properties), so the baseline of 4 applies. The description adds no parameter-specific semantics, but none are needed for a no-argument tool.

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 states a specific verb ('returns') and resource ('national FHA denial statistics for 2025'), then immediately provides the exact figure and universe. It explicitly excludes sibling scopes (conventional, VA, USDA, other years, state/lender/metro breakdowns), making it clearly distinguishable from tools like get_state_denial_stats.

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 opens with a list of example questions it answers ('how often are FHA loans denied') and includes an explicit 'NOT FOR' block naming exclusions and pointing to dedicated tools for breakdowns. This gives the agent unambiguous when-to-use and when-not-to-use guidance.

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