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

Annotations already declare readOnly/openWorld/non-idempotent/non-destructive, and the description adds material context on top: public DNS only, sends no mail, changes nothing, and a pricing model ($0.01/call via x402 USDC or card key, first 25 free, failed calls free) with the explicit warning that repeats are not free — which explains why idempotentHint is false. That cost/repeat behavior is exactly the kind of fact annotations cannot convey.

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 coverage list is front-loaded, followed by safety, usage triggers, example and price — a sensible decision order with no filler sentences. Minor redundancy: 'Reads or computes only and changes nothing' restates the readOnlyHint annotation, and the pricing block is dense enough to slightly dilute the core purpose statement.

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?

No output schema exists, and the description compensates by specifying the return shape: a 0-100 score, a grade, and a list of fixes. Combined with the enumerated checks, the DNS-only/no-mail guarantee and the cost model, an agent has everything needed to decide and call correctly.

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 goes beyond it by explaining what the optional email parameter actually triggers (syntax check, MX check, disposable-domain detection), which the schema's one-line 'Optional address to check as well' does not. The domain parameter is only illustrated by example rather than given extra semantics.

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 ('Email deliverability check for a domain') and enumerates exactly what is inspected: MX, SPF with all-policy, DMARC with policy, DKIM at named selectors, MTA-STS, TLS-RPT, BIMI. The enumeration plus the 0-100 score/grade/fixes output distinguishes it from adjacent siblings like dns_lookup, domain_report and pack_domain_intel without the agent needing to open any schema.

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 situations: 'before a campaign, when mail lands in spam, or to vet a sender domain', and adds a worked example (domain=github.com). It does not explicitly name a sibling as the alternative for narrower needs (e.g. plain dns_lookup or single-address email check), so it stops short of full when/when-not routing.

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