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

The annotations already declare readOnlyHint=true and openWorldHint=false, so safety and locality are covered structurally. The description adds content breadth (which rate families are returned) but omits materially useful behavior: HMRC AFR values are revised quarterly, and the word 'current' never says whether the payload carries effective dates or which period applies. It also says nothing about return shape or units, though the static nature of the data limits the risk.

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?

It is a single sentence with no filler, and the most-searched item (AFR by engine size) is front-loaded ahead of the electric rates and the THRIVE constants. The closing clause about 'the constants THRIVE's indices use' is slightly opaque to an outside reader but is not redundant. Nothing could be cut without losing a content category.

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 zero-parameter, read-only reference lookup with no output schema, the description covers what an agent needs to decide to call it: the full set of rate families it returns. The main omission is temporal — no mention of an effective date or update cadence for values that change each quarter. Adding that one clause would make it complete.

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 tool takes zero parameters, which is the baseline-4 case; there is nothing for the description to disambiguate. The description does implicitly confirm the no-argument design by framing everything as fixed reference categories rather than caller-selectable filters. No gap exists here.

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 resource and enumerates its three content groups: HMRC advisory fuel rates by engine size, advisory electric rates for home and public charging, and THRIVE's method constants. It is clearly a read-only reference lookup. It does not, however, distinguish itself from overlapping siblings such as get_fleet_rate_card or get_company_car_tax_rates, so an agent cannot tell from the text alone which of these to call.

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?

Usage is only implied: an agent can infer this is the reference-data call to make when it needs HMRC AFR or electric charging rates. There is no explicit statement of when to use this versus get_fleet_rate_card or get_company_car_tax_rates, and no note that it takes no arguments and needs no context. For a zero-parameter lookup the cost of a wrong pick is low, which keeps this at a minimum-viable 3 rather than lower.

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