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

Despite readOnly/openWorld annotations, the description discloses substantial behavior the annotations do not: the paid x402 USDC-on-Base model, three payer-passing options, the poll /v1/resolutions/:id until horizon_end flow, that an unpaid call returns a structured payment_required challenge (never fabricated data), and that a refusal refunds the debit. This is exactly the auth/payment/side-effect context an agent needs.

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 sentence 'After paying, poll /v1/resolutions/:id until horizon_end.' appears verbatim twice, and payment-rail mechanics are front-loaded ahead of the tool's actual purpose, forcing the reader past three clauses of billing before learning what is being assessed. Content is valuable but poorly ordered and visibly duplicated.

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 an output schema present, return values needn't be described, and the payment/polling flow is well covered. But for a tool with a required nested `candidate` object and an `address` parameter, the description omits what those inputs represent, which is a real completeness gap for a high-complexity, paid call.

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 description coverage is only 25% (only `asset` is documented in the schema), so the description carries the burden — and it explains only `payer` (a Base 0x… address). It never explains `address` (presumably the account to assess) or the required nested `candidate` object (tx_hash, log_index, direction, amount, etc.), leaving two required parameters semantically opaque.

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 names a concrete computation — the assessed ACCOUNT's liquidation proximity classified into {allow, review, block} with explicit thresholds (block ≤5%, review ≤15% or ≥5× leverage) read from clearinghouseState. That is specific and actionable. However, it never distinguishes this from the near-identical sibling tollbridge_liquidation_risk, and the name/title ('transaction_risk'/'account risk') mismatch adds avoidable ambiguity.

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?

Usage context is implied through the threshold logic and the pointer that exact USDC comes from tollbridge_pricing, but there is no explicit when-to-use statement and no routing against alternatives such as tollbridge_liquidation_risk or tollbridge_wallet_intelligence. The agent must infer the use case.

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