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

With no annotations at all, the description carries the full burden and does a lot of it: cost ($0.01/call), currency and chain (USDC on Base, eip155:8453), the exact payment channel (x402 in params._meta["x402/payment"]), a free sample path, and the concrete endpoint URL. This is exactly the kind of auth/cost context annotations would otherwise supply. It omits failure modes, rate limits, and what a successful paid response looks like.

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 payoff in the first clause, then pricing and transport in compact lines. Every element is substantive. It is dense to the point of being run-on in the pricing sentence, where USDC/Base/eip155/x402 are packed together without separation, but nothing is genuinely expendable.

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 2-param, no-output-schema tool with no annotations, the description covers what is checked, what it costs, how to pay, and where it lives. The remaining gap is call mechanics: with zero required params, an agent cannot tell from the description which argument selects /preflight versus /dns versus /batch.

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 both params are already documented in-schema, so baseline applies. The description adds only that /batch tops out at 10 domains — a constraint the schema also repeats — and never clarifies that 'domain' addresses /preflight or /dns while 'domains' addresses /batch. Notably both params are optional, and the description gives no indication of which one is needed for which path.

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 ('Trust check for any domain') and enumerates the exact data classes returned: DNS, SPF/DMARC/DKIM, WHOIS registrar/age, HTTP status, TLS issuer/expiry, HSTS. That is far more specific than a tautology. It does not, however, distinguish itself from adjacent siblings like domfacts__dns, domfacts__rdap, or domain_intel__batch, which an agent could reasonably confuse it with.

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?

It gives real selection context within the tool: free /preflight for a sample, paid /dns for the full report, /batch for up to 10 domains, plus the price. What it never says is when to pick this over domain_intel__batch or domfacts__dns, nor what the prerequisites are for x402 payment to succeed. Usage is implied by the endpoint/pricing breakdown rather than stated as guidance.

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