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

With no annotations, the description carries the full burden and does well: it explains the payout-list validity mechanic (UBI bought after the fix date counts from the next list), discloses the payment model for the per-wallet estimate ($0.003 over x402, or the card pass), and even discloses a conflict of interest ('We hold UBI and say so'). It leaves one ambiguity: whether this base call itself is free/read-only is only inferable from the contrast with the paid address variant.

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 core content is packed into one long run-on sentence with stacked parentheticals ('(UBI bought after that counts from the list after it)'), followed by an abrupt URL/price sentence and a one-line disclosure. It is dense rather than wasteful, but the lack of structure and a leading verb makes it harder to scan than it needs to be.

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, so the description must convey return contents — it does, listing contract USDC, next list validity and fix date, rate per 1M UBI, and recent payouts with wallets and amounts. Pricing and payment path for the per-wallet variant are covered. What's missing is return format (JSON shape, units, pagination/limits on 'recent payouts').

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% for the single optional address parameter, so the schema already explains that it returns the exact paid call for that wallet's estimate. The description reinforces that this path is a paid call and repeats the pricing, which adds a little context but no new parameter semantics (format, validation, defaults). Baseline 3 applies when the schema does the work.

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 the specific resource (UBI holder payouts on Arc via ubi.fun) and enumerates what it covers: USDC sitting in the payout contract, next payout list validity, USDC per 1M UBI, and recent payouts. It is clearly distinguishable from siblings like arc_holders, arc_price, or arc_yield by domain. It never states a verb (fetch/read), presenting the tool as a topic list rather than an action, which keeps it short of a 5.

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 is implied by the subject matter — call this for UBI payout state on Arc. The description does add one explicit routing rule: for a per-wallet payout estimate, use the paid x402 GET endpoint with the address, rather than expecting it from this call. It names no sibling tools and gives no when-not-to-use guidance (e.g., versus arc_holders for raw holder lists), so the guidance is partial.

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