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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered by structured data. The description adds context an agent genuinely cannot get elsewhere: the upstream series identity (DJFUELUSGULF), the units (USD/gallon), and an explicit metering/authorization model — $0.002 USDC per successful call via x402 on Base, Solana or Arc, with failed calls uncharged. That payment detail is exactly the kind of pre-call knowledge an agent needs, though freshness/caching behavior is left implicit in 'daily'.

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?

Three front-loaded sentences: what it is, what it is not, then cost. The final sentence is dense (payment rails, currency, failure policy) but every clause is decision-relevant for an agent about to spend money. Minor cost: the parenthetical blockchain list is stacked into one long clause.

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?

An output schema exists, so return-value structure need not be explained, and the description supplies source, geography, unit, cadence and cost. Remaining gaps are small but real: no statement of publication lag (EIA daily series typically publish with a delay) or whether the history window is calendar days or observations, which matters given the 'days' parameter.

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% and the single parameter 'days' is fully documented in-schema (1-30, default 7). The description adds only the qualitative phrase 'recent history', which does not extend the parameter's meaning. Baseline 3 is appropriate when the schema carries the semantics.

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 resource with full provenance: 'Daily US Gulf Coast kerosene-type jet fuel spot price (USD per gallon) from FRED (US EIA series DJFUELUSGULF): latest value and recent history.' It also explicitly rules out the most likely confusion ('not a Jet-A1 or European refinery index'), which lets an agent separate it from siblings like energy_crude_oil_brent_wti or logistics_fuel_bunker_prices 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?

The negative disambiguation ('US Gulf Coast benchmark, not a Jet-A1 or European refinery index') is genuine routing guidance and is the main failure mode for this tool. It stops short of naming a positive alternative or stating when to prefer logistics_fuel_bunker_prices for bunkering use cases, so the guidance is clear but not exhaustive.

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