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

Adds real behavioral context beyond the annotations: per-match pricing with free misses, batch bounds, and a single x402 settlement tied to the hit count. It does not cover partial-failure/refund behavior or whether a miss-heavy batch still settles once, and charging money under readOnlyHint=true is an implicit tension worth flagging to the agent.

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 sentences, cost first, then input shape, then what you get, then settlement — a sensible front-loading. Slightly telegraphic phrasing ('PAID $0.01 per input that finds a business') but nothing wasted.

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?

An output schema exists so return values needn't be explained, and the description covers pricing, batch limits, and what a match contains. The one real gap is failure semantics: what happens if some records error, and whether the settlement still fires once.

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 the description largely restates it ('1-100 websites or US phone numbers' mirrors the records min/max and the domain/phone fields). It adds no format guidance (URL vs bare domain, E.164 vs digits) or handling for the 'exactly one key per record' rule beyond what the schema already says, so the baseline 3 applies.

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 ('enrich', leads) with the 'bulk' scope and concrete input types (1-100 websites or US phone numbers). It implicitly distinguishes itself from siblings like leads_lookup/leads_search/leads_count via the batch framing, but never names those siblings, so the differentiation is inferred rather than 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 1-100 batch limit and 'US phone numbers' constraint imply when this tool is appropriate (bulk enrichment, US-only phones), but there is no explicit when-to-use guidance and no reference to leads_lookup or leads_search as the single-record alternatives. The agent has to infer routing.

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