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

Annotations already declare readOnlyHint=true, so the description correctly does not repeat that. It adds significant behavioral context: experimental status, exclusion from accuracy eval, potential to change or be withdrawn, the $0.05 per-call cost, and the limitation to network fee only. These go well beyond the structured fields and set accurate expectations for an agent.

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 description is a single, dense sentence that packs multiple important clauses (cost, chains, metric, exclusions, price, experimental caveat). Every clause carries useful information with no filler, though the density could be seen as slightly heavy. It is front-loaded with 'Experimental' to set expectations immediately, which is effective.

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 one-parameter tool with no output schema, the description is remarkably complete. It explains what is returned conceptually (USD costs per chain and identification of the cheapest), sets a clear boundary (network fee only), and flags all critical caveats (cost, experimental, not a quote). An agent has everything needed to decide whether and how to call it correctly.

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%: the only parameter 'chains' is fully described in the schema (comma list, allowed values, default). The tool description adds no additional parameter-level detail beyond that, so it meets the baseline of 3 but does not exceed it.

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 clearly states the specific verb ('Compare live network fees'), the resource ('across Base, Arbitrum, and Ethereum'), and the metric ('USD cost of a standard native transfer'). It also explicitly names the output concept ('cheapest chain named'), which distinguishes it from a generic gas-price tool like evm_gas. The mention of 'not a route or swap quote' further disambiguates it from swap-related tools.

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 description provides strong usage context: it is for comparing gas costs across chains, with a cost per call and experimental status. It explicitly states it is not a route or swap quote, which is a clear exclusion. However, it does not explicitly name alternatives (e.g., evm_gas for single-chain gas price) or give a 'when not to use' beyond that, so it earns a 4 rather than 5.

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