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

Since no annotations exist, the description carries the full behavioral burden and does so thoroughly. It discloses the source dataset, filtering logic (actions 1,2,3; loan_type 2), the observed-rate caveat, lack of adjustment, the machine-readable claim-passport format, and the no individual prediction limitation.

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 dense but mostly efficient: core function, output contract, data provenance, limitations, and licensing are all packed into a few loaded sentences. It loses a point for slightly encyclopedic style, but every major clause contributes either a constraint, a caveat, or a usage boundary.

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 present, the description must explain both the output fields and the interpretation. It lists the lowest and highest lender counts, gap percentage points, source-record hash, interpretation boundaries, and a link to the claim contract. Combined with the single-parameter schema, this is fully sufficient for an agent to invoke and interpret the result.

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 documents the metro parameter at 100% coverage. The description additionally clarifies that valid metros are limited to 184 markets and that smaller markets are excluded by the volume floor—useful context for interpreting invalid or out-of-scope metro values.

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 opens with a specific object: a per-metro FHA denial-rate gap between high-volume lenders, with a concrete threshold and year. It clearly distinguishes itself from address-level, state-level, or national-level siblings by making the metro scope and comparison-based output explicit.

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?

The description gives clear context for when the tool applies: only to the 184 covered metros and only to high-volume lender gaps. It also states what it is not (a prediction about any individual application), which serves as a when-not boundary. It does not name sibling tools or give explicit alternative conditions, so it stops just short of tournament-level 5.

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