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

Annotations only cover readOnly/openWorld; the description adds the operationally critical context an agent needs: cost ($0.002 USDC per successful call via x402 on Base/Solana/Arc), that failed calls are not charged, and the block-range ceiling. That is exactly the kind of payment/auth and limits detail structured fields do not carry.

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?

Scope, data source, event types, cost model and caveat are all packed into a few sentences with the core payload front-loaded. The mid-sentence parenthetical event list and pricing tail make it slightly dense, but no sentence is 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?

With an output schema present, return-shape explanation is not needed; the description still covers scope, time window limits, data provenance, and billing behavior — everything an agent needs to call it correctly and know what it costs.

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 the single 'blocks' parameter already documents its range and default, so the description only restates the bounds and the '~4 weeks' interpretation. Baseline 3 is appropriate — the schema does the heavy lifting.

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 verb and resource — USDT (Ethereum) supply changes derived from the contract's own events — and enumerates the event types (Issue, Redeem, DestroyedBlackFunds) plus the aggregates returned. This is specific enough to separate it from stablecoin or treasury-report siblings without opening the schema.

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?

It gives a clear usage boundary by stating 'On-chain events only, not Tether's treasury reports' and by defining the block-window semantics (1–200000, ~4 weeks), which tells an agent when the tool applies. It stops short of naming an explicit alternative sibling for the off-chain/treasury case, so it is not a full when/when-not pairing.

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