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

Goes well beyond the readOnly/openWorld annotations: discloses data provenance (eth_feeHistory over 20 blocks, Solana prioritization fees), a 15-second cache, the $0.002 USDC x402 charge, and that failed calls are free. Cost and freshness are exactly the behavioral facts an agent needs before calling.

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?

Chain coverage and output fields come first, then provenance, caching, and pricing as separate short clauses. Dense but every sentence carries non-redundant information; nothing is padding.

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 read-only, one-parameter tool with an output schema, this covers everything material: scope, default, data sources, cache staleness, and payment mechanics. No gaps an agent would need to guess at.

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?

The single parameter is already fully documented in the schema, so baseline is 3; the description adds the useful fan-out semantics of chain=all ('every chain at once') and reinforces the default. Little beyond that, since the enum of chains is duplicated from the schema.

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+resource ('Gas prices') and enumerates exactly which chains are covered, plus what the response contains (base fee, slow/normal/fast priority fees, latest block, transfer costs). An agent can distinguish it from btc_fees or defi_fees without opening a 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?

Makes the default explicit ('Base (default)') and explains that chain=all returns every chain at once, which is the main usage decision point for this tool. It never names an alternative sibling such as btc_fees for Bitcoin or defi_fees, so exclusion guidance is missing.

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