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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=true and idempotentHint=false; the description goes further by disclosing cost ($0.01/call via x402 or card key, first 25 free, failed calls free), the HTTP 400-without-charge behavior on invalid values, and that repeat calls are billed (consistent with idempotentHint=false). That is real added value. However, it never says what the response contains or whether fee data is cached/stale, so it does not fully carry the behavioral burden left by the annotations.

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 the core action, then assumptions, valid values, exclusions, usage, example, and pricing in a logical order with no filler sentences. It is dense to the point of feeling packed — pricing and error-handling details sit in the middle of the capability description — but nothing is redundant given the lack of an output schema.

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 this covers scope, assumptions, valid inputs, cost, and failure behavior well. The clear gap is the return value: with no output schema, the description should say roughly what a gas estimate response looks like (fields such as gas cost, priority fee, total), and it only says 'estimates gas costs'.

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% and the enum values are already listed, so the schema establishes the baseline. The description nonetheless adds meaning: high-mev means 3x priority fee, low-gas means half, and invalid values return HTTP 400 without charge — semantics an agent cannot infer from the bare enum. It does not explain what 'standard' maps to beyond 'current fees', which keeps it short of a 5.

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 — 'Estimates Base gas costs from current fees and priority-fee presets' — and immediately bounds the claim by noting the fixed gas-unit assumptions are typical rather than transaction-specific. It also rules out adjacent capabilities ('No transaction simulation, mempool observation, or MEV/sandwich-risk measurement'), so an agent can distinguish it from the risk/analysis siblings despite the MEV-flavored name.

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 to budget gas for a Base transaction' gives the positive trigger, and the negative clauses (no simulation, no mempool, no sandwich-risk measurement) tell the agent when this tool is the wrong pick even though its title mentions MEV. An example invocation (scenario=standard) anchors the call.

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