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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds genuinely new behavioral context: the upstream source (eth_feeHistory), data freshness (live), the averaging window (10 blocks), units (gwei), and a per-call price with a free first call. Rate limits, caching, or failure behavior for the paid endpoint are not disclosed.

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?

Two sentences, zero waste, and front-loaded: the payload is stated first, the cost second. Every clause carries information an agent needs to decide and to predict the response.

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 usefully enumerates the returned values and their units, plus the data source, freshness, and price. It could go further on what the congestion label's values mean and whether fields can be absent, but for a zero-parameter read-only feed it is nearly 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?

The tool takes zero parameters, so the 4 baseline applies; there is nothing to disambiguate. The description instead documents the return fields, which is a bonus rather than a parameter requirement.

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 the resource (live Base Mainnet gas data) and enumerates exactly what is returned: latest and 10-block average base fee in gwei, p25/p50/p75 priority-fee percentiles, and a congestion label. It is plainly distinct from every sibling (contract-profile, dex-arbitrage, whale-wallet-tracker), though it never names or contrasts a sibling, keeping it short of a 5.

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?

Usage is only implied: an agent can infer it is the go-to source for gas pricing when timing or costing a Base transaction, but there is no explicit when-to-use statement or reference to alternatives. The cost note (0.0020 USDC, first call free) is useful call-planning context but is not usage guidance per se.

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