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

Annotations already declare a safe, idempotent read, and the description adds substantial context beyond them: the underlying data source (CFPB HMDA 2025, actions 1,2,3; loan_type 2), the disclosure limit on unpublished middle bands, the caveat that it is not a prediction about an individual application, and the observed 1.19x–4.45x range.

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?

It is front-loaded and sectioned (ANSWERS / PARAM / Returns / NOT FOR / attribution), so it scans well. It runs long, however — the four sample queries and the specific Idaho figures are retrieval aids that border on padding for an agent that already has the title and schema.

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 burden and does so: denial rates for both bands, the ratio, the ranking, and a discrepancy note. Combined with the methodology and caveats, an agent has everything needed to call and interpret it.

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% and there is a single optional param, so the baseline is 3; the description earns extra by explaining what omitting the parameter produces (a ranked list), which the schema's 'optional' marker does not convey.

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 computed metric (small-loan denial penalty, i.e. denial-rate ratio for small vs large loans) scoped by state, and names the exact bands (<$150K vs >$250K). It is clearly distinguishable from siblings like get_state_denial_stats or get_national_fha_stats, which do not isolate the size penalty.

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 gives an explicit selection rule ('optional two-letter state; omit for the ranked list') and a clear exclusion ('NOT FOR: loan sizes between the bands, which are not published'). It stops short of naming an alternative sibling for the excluded case, so it is strong but not fully routing.

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