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

With readOnlyHint=true already declaring the safety profile, the description adds real behavioral context beyond the annotations: a 7-day data lag, an up-to-100-record cap, and removal of individuals' names, phones and some street addresses. It does not state pagination or whether truncated results are flagged, but the added disclosure is substantial.

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 sample nature, delay, and free/capped status are front-loaded, and the feed list is dense but each entry adds distinct routing information. The trailing standalone 'Free.' is redundant with the opening 'Free 7-day-delayed sample'.

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?

For a read-only sample tool with no output schema, the description covers the essentials an agent needs: what a feed returns, what PII is stripped, the record cap, and region granularity. Only the days window and any truncation/pagination behavior are left unaddressed.

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%, so the baseline is 3. The description genuinely enriches the feed enum (mapping each key to a state/agency source) and clarifies that region accepts a county, city or Chicago community area, but it never mentions the 'days' parameter or its 1-60 window, leaving one parameter's semantics entirely to the schema.

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 gives a specific verb/resource ('free 7-day-delayed sample' from one feed) and enumerates exactly what each feed key returns, so the agent knows it is fetching preview business-lead data. The 'sample' vs. the sibling 'new_business_leads_fresh' is implied by the 7-day delay and free framing, but the alternative is never named, so sibling differentiation is left to inference.

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?

Constraints (free, delayed, PII stripped, capped at 100 records) implicitly signal this is a preview/evaluation call rather than a production data pull, which is useful context. However, it never states when to choose this over new_business_leads_fresh or buy_info, nor any prerequisites or exclusions.

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