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

Annotations already declare readOnlyHint=true and openWorldHint=true, but the description adds material context beyond them: a $0.002 USDC per-call charge collected inline via x402, the accepted payment chains (Base, Solana, Polygon, Arbitrum), and automatic settlement by x402-capable clients. This is exactly the payment/authorization behavior an agent needs before invoking.

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 core capability and return contents before moving to payment mechanics and the free sample. Sentences are dense but each carries distinct information (scope, payload, cost, payment path, example); nothing is redundant padding.

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?

With no output schema, the description usefully enumerates every returned field, and it covers pricing and a worked example. It stops short of stating failure modes (invalid or non-existent digest, what a payment failure returns), which leaves a small gap for a paid, single-purpose lookup.

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?

Only one parameter exists, and schema description coverage is 100% ('Transaction digest (base58)'), so the schema carries the semantic burden. The description adds a concrete sample digest value, which helps validation, but no further format or constraint detail beyond what the schema gives. 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 and resource ('Sui mainnet transaction by digest') and immediately enumerates the returned payload (status, time, checkpoint, sender, Move calls, gas, balance changes, objects, events). This clearly differentiates it from sibling lookups such as evm_tx, btc_tx, iota_tx, and the address/network siblings sui_address and sui_network.

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 description documents how to call it (pass a digest, or reuse the free example input) but never states when to prefer this over alternatives like sui_watch or sui_network, nor does it define when the tool is inappropriate (e.g., non-mainnet digests). Usage is implied by the input rather than explicitly routed.

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