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

With no annotations, the description carries the full load and does well: it names the exact evidence sources (ERC-8004 operator, on-chain distinct payers, live x402 probe, uptime, Hyperliquid record, bond, OFAC), which tells the agent how trustworthy the verdict is. It also discloses cost ($0.005), a rate limit (5 free/day), and the faucet for free credits — genuinely useful behavioral context beyond the schema.

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 verdict/return shape before the data-source list, and the pricing detail is correctly relegated to the end. The evidence list is a dense run-on, but every element listed is a distinct signal an agent would want, so it earns its length.

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 defining the return shape (verdict, two strongest reasons, numeric score). Cost, free quota, and source coverage are all present; only failure modes and response latency are unaddressed.

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 each parameter already documents its meaning ('or its ERC-8004 agent id', 'or the seller payTo'). The description only restates the one-of constraint, adding little beyond what the schema provides, so the 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+resource+output: 'Check before you pay another agent' returning pay/caution/avoid, two reasons, and a 0-100 trust score. It is clear what the tool does and roughly what it returns, but it never names the near-identical siblings (arc_trust_check, x402_seller_check, arc_counterparty, x402_payment_test) that an agent must choose between.

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?

'Check before you pay another agent' gives a clear trigger condition, and 'Pass ONE of url / address / agent' supplies an operational rule. What is missing is explicit routing against alternatives — nothing says when to prefer x402_seller_check or arc_reputation instead.

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