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

Annotations already cover safety (readOnlyHint true, destructiveHint false), and the description corroborates and enriches them: it declares the tool computes only and changes nothing, explains the non-idempotency hint (each call is charged, repeats are not free), details pricing/credits, and specifies the revert outcome. This is materially more than the structured fields provide.

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 purpose and an example address, then usage, error behavior and cost. It runs long for a 4-parameter tool, and the charging model is stated twice ('each call is charged, so repeats are not free' after the x402/free-tier sentence), a minor redundancy in otherwise tight prose.

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, so the description carries the return-value burden — and it does, naming the three units returned (gas units, gwei, ETH). Combined with the revert/error contract and cost model, an agent has everything needed to call this 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 coverage is 100%, so the baseline is 3. The description lifts it by explaining intent rather than types: value is in ETH, calldata goes with a contract call, and 'from' is only needed 'when the call depends on it' — nuance the schema's 'default: an empty address' does not convey.

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 ('Estimate the gas a transaction would use on Linea') and names the underlying RPC (eth_estimateGas), extending the scope to cost in gas units, gwei and ETH. It explicitly distinguishes itself from the sibling linea_gas, which the agent can act on without opening either 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?

'Use before sending a transaction or to price a batch' gives the triggering contexts, and 'for the gas price alone use linea_gas' names the alternative with the condition that selects it. The revert behavior (422 with reason, uncharged) tells the agent what a failed attempt looks like rather than leaving it to inference.

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