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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful non-annotation context: it is a paid per-call asset at $0.08 USDC (or prepaid credits) and payment must travel in MCP headers (X-Payment / X-Payment-Tx / Authorization: Bearer fg_…), explicitly not in parameters. That is strong. What is missing is any statement about failure modes — what happens on an unpaid call, rate limits, or whether results are cached.

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 payload is front-loaded well, opening with the user-style question and the metric list, which is the right order. But the definition is padded: the same tool is re-described in [zh] and [en] blocks that restate the vendor asset name, price and the 'chains' argument already given, and the payment-headers sentence sits after the repetition. It is serviceable but noticeably bloated.

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?

There is no output schema, and the description compensates by enumerating every returned metric, the cheapest-chain summary, the gas-usage assumptions and the FX basis — so an agent knows what comes back. Pricing and the auth mechanism are also covered. The remaining gap is the chains parameter format and the choice relative to gas_now, but for a single-parameter read-only report this is close to complete.

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 0% and there is one parameter, so the description carries the full burden — yet it only repeats 'chains is optional' three times across the bilingual blocks. It never says what the value should look like: a comma-separated list, chain slugs versus ids, or what the null default means (all six supported chains?). An agent cannot reliably populate this parameter from the definition.

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 resource (gas across chains) and enumerates exactly what the report contains: gas price, base fee, priority fee in gwei, block height, RPC latency, USD cost for three canonical transaction types, the cheapest chain, gas-usage assumptions and native-currency conversion. That is far more specific than the name alone. It does not, however, contrast itself with the obvious sibling gas-board.gas_now, leaving the agent to infer that this is the 'full' versus 'snapshot' variant from the word 'full:' only.

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?

The opening 'Ask "what is gas price on each chain"' gives a concrete trigger scenario, which is real usage context. But there is no when-not guidance, no prerequisites, and no named alternative — the definition never tells the agent to use gas_now for a quick single-value check and this tool when a complete cost breakdown is needed.

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