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

Annotations already cover read-only, idempotent, non-destructive and open-world, and the description adds substantial context beyond that: what is simulated (reverts, assets out, approvals), what is decoded (permit phishing), chains covered, the three-tier verdict, and the free-tier limit of 10 calls per day before it returns an x402 pay-per-call endpoint and price. That rate-limit and fallback behavior is exactly the operational detail 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?

Front-loaded with the decision question and the imperative to call it once, then dense supporting detail. The middle sentence is long and clause-heavy, but each clause carries distinct behavioral information rather than filler.

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 an eight-parameter, nested-object tool with no output schema, the description covers the return contract (one proceed/caution/avoid verdict with reasons), supported chains, and the free-tier boundary. Nothing critical for correct invocation is missing.

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 already 88%, so the bar is low, but the description earns credit by explaining what happens to each input category: transactions are simulated, typed data is checked for permit phishing, recipients are screened against sanctions and scam lists, and tokens are rug-checked. It also clarifies the non-obvious 'including tokens the simulation shows the wallet receiving', though expectedMaxUsd (the one undocumented parameter) is not explained anywhere.

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?

The description opens with a concrete question ('Is this action safe?') and states the resource: a preflight verdict over transactions, typed data, x402 payments, recipients and tokens. The all-in-one verdict framing implicitly separates it from narrower siblings such as tx_simulate, address_check or signature_check, but none of those siblings is named explicitly.

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?

'Call once before any on-chain action' gives a clear, actionable trigger, and it enumerates which inputs belong together in one call. It stops short of naming alternatives (tx_simulate, wallet_safety, approval_scan) or stating when not to use it, so the agent must infer the routing.

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