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

Goes well beyond the annotations: pricing model ($0.002/call via x402 USDC or card key, first 25 free, failed calls free), output ordering (cheapest first), the USD conversion source (Uniswap ETH price), and the explicit warning that repeats are not free. That last point is consistent with idempotentHint=false and readOnlyHint=true, and 'reads or computes only and changes nothing' reinforces the non-destructive profile.

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 coverage and returned fields, and every clause is informative. It is a single dense run-on that mixes output spec, marketing ('Cheaper than the tools bought one by one') and billing terms, so a little tightening would help readability.

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 no output schema, the description fully compensates by naming every returned field, its unit (gwei, native coin, USD, sat/vB) and its ordering. Cost and billing terms are present too, which matters for an agent deciding how often to call. Nothing needed to call it correctly is missing.

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?

There is a single optional 'only' projection parameter, and its schema entry already documents the comma-separated key syntax and the fallback to a full result at 100% coverage. The description never mentions it, but the schema carries the weight, so 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 and resource ('One call for current gas prices') plus exact chain coverage (Base, Ethereum, Arbitrum, Optimism, Polygon, Bitcoin) and the returned fields (gas price, base fee, priority fee, transfer cost in native coin and USD, BTC sat/vB). This clearly distinguishes it from the single-chain siblings like eth_gas, base_gas and btc_fees.

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?

Gives three concrete use cases (pick the cheapest chain, time a transaction, show fees in a wallet) and positions itself against the per-chain tools ('Cheaper than the tools bought one by one'). It stops short of an explicit exclusion such as 'use eth_gas if you only need one chain', so the alternative routing is implied rather than stated.

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