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 discloses data provenance ("from our launch history"), the meaning of the two derived metrics (first-sight risk score, venue-level count of pools that lost liquidity within 24h), a data-quality caveat ("quote liquidity where readable"), a trust warning (spam prevalence), and the payment mechanism ($0.01 USDC on Base via x402). It stops short of stating whether the charge applies per call, per failed call, or how empty results behave.

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 purpose and chain are front-loaded, and the payment/spam caveats are short and useful. The middle field enumeration is a long run-on list, but each item is genuinely informative about the payload, so little is wasted.

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 a 2-parameter read tool with no output schema, the description adequately covers what is returned, where the derived risk numbers come from, and the payment requirement. Remaining gaps (empty-result behavior, per-call billing details, ordering/pagination beyond "newest first") are minor.

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 100% and both parameters already document ranges and defaults, so the baseline applies. The description only echoes the "last N minutes" notion of the minutes parameter and adds nothing about limit ordering or the 12,000-block cap beyond what the schema states.

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 specific resource and scope ("new trading pools created on Arbitrum One in the last N minutes") and enumerates the venues covered (Uniswap v4, v2, v3), which cleanly separates it from the sibling chain variants (base_new_pools, eth_new_pools, polygon_new_pools) and from token_risk_check/token_verdict. It also lists the returned attributes (both tokens with symbol/name/decimals, fee tier, v4 hooks, ETH/WETH/USDC pairing, quote liquidity), so an agent knows exactly what it gets.

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 only implied: the recency framing suggests a discovery/monitoring use case, and the "Unvetted: many new pools are spam" line hints at caution, but no sibling tool is named as an alternative and no when-not-to-use condition is stated (e.g. use token_risk_check for a deeper verdict). The cost note gives a practical constraint but is not selection guidance.

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