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

Annotations already cover safety (readOnlyHint, idempotentHint, destructiveHint false, openWorldHint false), and the description adds genuinely new context beyond them: the exact legal provisions applied and the explicit warning that this is 'a planning aid, not an official classification'. That reliability caveat is the kind of behavioral disclosure annotations cannot carry. It stops short of describing the answer's shape or edge-case behavior (e.g. ambiguous inputs), which keeps it from a 5.

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?

Two sentences, zero filler, and the operative content (what it classifies, under which article, and what the answer includes) is front-loaded before the caveat. Nothing repeats the title or the schema.

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 seven-parameter, read-only lookup with no output schema, the definition supplies the regulatory basis, the category set, the passport-determination output, and a reliability caveat. There is no output schema, so a brief note on the response shape would have closed the last gap, but nothing an agent needs to call it correctly is missing.

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 every parameter already documents itself, including the use enum and the industrial/capacity_kwh pairing. The description's category list (LMT, electric vehicle, SLI, portable, industrial) loosely maps onto those enum values and the industrial flag, which helps an agent connect the legal taxonomy to the inputs, but it adds no further format or validation detail. Baseline 3 applies.

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 (classifies) and resource (a battery), pins the legal basis to Art. 3 of Regulation (EU) 2023/1542, enumerates the resulting categories (LMT, EV, SLI, portable, industrial), and states the secondary output (passport obligation under Art. 77). That is far more specific than any sibling such as check_duties or check_gpsr_information, so an agent can route to it 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?

The use case is strongly implied — you call it when you need to know a battery's regulatory category or whether a passport is required — but there is no explicit when-to-use/when-not-to-use statement and no named alternative within the sibling set. The closing caveat routes the agent on trust level rather than on tool selection, so guidance stays implicit.

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