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

The annotations already declare readOnlyHint=true, idempotentHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that — sort order (lowest first), inclusion of observation time, and the caveat that these are reference prices for sample areas rather than address-specific quotes. It does not say how many suppliers come back or whether results are paginated or truncated.

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 usage trigger, then coverage, return shape, and the caveat — a sensible ordering with no filler sentences. The middle sentence restating the litre ranges per nation duplicates the schema almost verbatim, which is the only wasted 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?

With no output schema, the description takes on the burden of describing the return value, and it does so adequately: pounds, delivered totals, grouped by supplier and area, sorted ascending, with observation time. The main residual gap is result volume and whether a full supplier list or a sample is returned, which matters for a price-comparison tool.

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 input schema has 100% description coverage and already documents the litre sizes per region and the BT postcode/Northern Ireland mapping, which the description largely restates. The one piece of added meaning is the operational implication that certain litre values are only valid in certain nations, but that is inferable directly from the enum and descriptions.

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 the resource (home heating oil / kerosene prices), the exact geography served (Northern Ireland, England, Scotland, Wales) and the unit of return (delivered totals in pounds by supplier and area). It also explicitly hands off the Republic of Ireland case to tankful_county_supplier_prices, so an agent can separate this from at least one close sibling without reading schemas.

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?

Opens with an explicit trigger ('Use this when someone asks about home heating oil or kerosene prices...') and gives a clear exclusion with the named alternative for Republic of Ireland queries. It does not state how this differs from tankful_national_prices or tankful_county_supplier_prices, both of which sit in the same price family, so the routing is only partially resolved.

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