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

The readOnlyHint annotation covers the safety profile, and the description goes beyond it with genuinely useful behavior: a hard cap of up to 300 records, a per-call cost of $0.99 USDC, and the x402/Base payment mechanism required to invoke it. Payment/auth requirement disclosure is exactly the kind of context annotations cannot carry; only the absence of any latency or rate-limit detail keeps it from a 5.

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?

Four short, front-loaded sentences with no filler: feeds first, then filters, then volume, then price. Efficient, though the run-on filter clause is slightly compressed at the cost of readability.

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 does the work of indicating the return shape ('up to 300 records with full details') and the payment prerequisite. Combined with a 75%-documented schema, an agent has nearly everything needed; only the fresh-vs-sample selection rule is missing.

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 75%, so the baseline is 3. The description restates what the schema already documents (region, kind as type text match, days 1-30 default 3) without adding syntax, format, or examples beyond it – e.g. it doesn't clarify that region accepts county, city, or community area.

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?

States a specific verb+resource (current records, no delay, from one feed) and enumerates the six available feeds, so the agent knows exactly what data it returns. The '(no delay)' framing implicitly differentiates it from the sibling new_business_leads_sample, though the fresh-vs-sample distinction is never made 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 operational parameters (filters, record cap, price) but never states when to use this tool versus new_business_leads_sample or the other fresh/sample sibling pairs. Usage is implied by '(no delay)' rather than stated as guidance or exclusions.

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