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

Annotations already declare this a safe, idempotent, closed-world read, so the description's job is to add coverage detail — which it does well: it discloses the granularity returned (500 L and 1,000 L), the aggregates (typical, lowest, weekly medians), a quote link, and the important limitation that only suppliers who publish prices are included. It stops short of stating whether prices include VAT or delivery charges, which is a material omission for a price-comparison tool.

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?

Four sentences, front-loaded with the trigger condition, then returns, then scope exclusions. The HVO sentence and the forecourt exclusion both earn their place as routing constraints rather than filler. No redundant restatement of the tool name or title.

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 must convey return shape — and it does (per-litre prices at two volume tiers, typical/lowest, weekly medians, quote link). Combined with the 100%-covered single parameter and full annotation set, an agent has enough to select and call this correctly. The missing pieces are commercial semantics (VAT/delivery inclusion) and data freshness beyond "weekly".

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 single enum value carries its own explanation (GREEN_DIESEL = marked gas oil for farms/plant/heating; ROAD_DIESEL = road vehicles), so the schema does the heavy lifting. The description reinforces the same distinction in prose but adds no new meaning such as which fuel type applies to which enquiry pattern. Baseline 3 is appropriate.

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?

The description names a specific verb and resource — per-litre green diesel (marked gas oil) and delivered road diesel prices for farms, businesses and fleets in Ireland — and immediately bounds the domain with two exclusions (forecourt pump prices, HVO). An agent can tell this apart from siblings like tankful_uk_prices (Ireland scope) and tankful_county_supplier_prices (supplier-level rather than national price data) without opening the 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?

There is an explicit activation condition ("Use this when a farm, business or fleet in Ireland asks about...") and an explicit exclusion ("Do not use for pump prices at forecourts"), plus a scope note that HVO is unavailable. It falls short of 5 because it never names the sibling that handles the excluded cases, so the agent must infer where to route a forecourt-price question.

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