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

With no annotations, the description carries the burden well: it discloses data provenance (two lists pinned to a commit, live MX/SPF/DMARC), scope limits (no SMTP probe, so mailbox existence is not verified), auth/cost model (no API key, $0.005 per call via x402/USDC), and the structure of the result. It stops short of error modes, timeouts or rate limits, which matters somewhat for a paid network-dependent call.

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?

Front-loaded with the decision context, then verdict semantics, then provenance, then cost — a sensible order with almost no filler. The exact list counts (12,141 / 4,897 / 1,018) are slightly noisy but do signal maintained coverage, so they mostly earn their 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?

There is no output schema, so the description must describe return values itself — and it does: a 0-100 score, an enumerated verdict, and per-point evidence tied to the proving field. Combined with the pricing and no-key disclosure, an agent has everything needed to call and interpret it.

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?

One parameter at 100% schema coverage, so the schema already documents the input fully. The description reinforces the one-address-per-call granularity ('scores one email'), but adds no syntax, normalisation, or batching semantics beyond that.

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 and resource: scores one email 0-100 with a named verdict set (ok, risky, disposable, undeliverable, invalid) and itemised evidence. It is unmistakable against siblings like red_domain_check, red_dnsbl or red_asn, which operate on different subjects.

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?

Gives concrete triggering decisions — before writing to an address, or cleaning a list before sending — so the agent knows when to reach for this rather than a generic DNS or domain tool. No explicit exclusions, but the use contexts are sharply drawn enough to route correctly.

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