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

Annotations already declare readOnlyHint and idempotentHint, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: results are cumulative across measures in a stated order, and each of car/heating/solar/battery is interpreted as either something the home has (explaining the bill) or something being considered. It does not mention any cost, latency or determinism beyond the idempotent annotation.

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 sentences, no filler, and the core computation is front-loaded. However, the parenthetical '(tariff, car, heating, solar, battery)' and the nested clause 'Each of car, heating, solar and battery is something the home has (it explains the bill) or is considering' make it noticeably hard to parse on first read, which works against a tool an agent must interpret quickly.

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?

There is no output schema, so the description bears some burden for describing returns; it gives one sentence on what totals are and that only changes are counted, but not the response shape, per-tariff breakdown, or units. For a 68-parameter, highly interdependent planning tool, the description is adequate but leaves meaningful gaps an agent would want covered.

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%, so the 68 parameters are already documented in detail, including defaults, ranges and conditional applicability. The description adds only a marginal framing statement ('Totals are electricity, gas at the price cap and petrol or diesel – only what changes') and does not clarify the cross-parameter dependencies (e.g. consider_ev, consider_heat_pump gating) beyond what the schema already says. 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 computation: a home's past year on every tariff in list_tariffs and at the price cap, plus savings from switching, an EV, a heat pump, solar or a battery, applied cumulatively. That is far more than a restated title. It stops short of a 5 because it never contrasts itself with the siblings that overlap it most (plan_home_battery, plan_ev_charging, plan_home_solar-style single-technology planners), so an agent must infer that this is the whole-home, all-measures variant.

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 implied rather than stated: the phrase 'each added to everything before it (tariff, car, heating, solar, battery)' hints at a cumulative whole-home scenario, which suggests using this over the narrower sibling planners. There is no explicit when-to-use, when-not-to-use, or named alternative. An agent can guess the context but is given no routing rule.

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