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

With no annotations, the description carries the full burden and does so thoroughly: it discloses return fields, data source, computation details, licensing restrictions, and important limitations like 'not a prediction' and 'screening signals, not findings of misconduct'. It even tells agents they can relay a purchase offer but cannot complete a purchase.

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 front-loaded with example queries and packs many important constraints into a compact paragraph. It is slightly dense and mixes legal/methodological caveats with operational guidance, but every sentence earns its place.

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?

Given that there is no output schema and no annotations, the description is unusually complete: it states input constraints, output items, licensing behavior, data source, and interpretive limits. An agent has enough context to decide whether to call this tool and how to interpret its results.

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 schema already covers all parameters at 100%, so the baseline applies. The description adds useful domain context about public identifiers and the licensed Evidence Brief, but it does not meaningfully extend the per-parameter meaning beyond what the schema provides.

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 clearly identifies the tool as screening a list of public LEIs against the federal HMDA record and returning observed-versus-expected FHA denial rates. It distinguishes itself from nearby stats tools by framing its purpose as 'which of my counterparties deny more than their applicant mix predicts'.

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 natural-language examples make it clear when to invoke this tool, and the description gives strong context about acceptable inputs and the licensing boundary for the full Evidence Brief. It does not explicitly name sibling alternatives or state when not to use them, so it stops short of full when-versus-alternative routing.

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