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

Annotations already carry the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's added value is what it discloses beyond that: answers come from a curated rules table with a cited Act section per rule, supplementary material is pulled from the GetLawED library, and it states plainly when no rule matches. The one gap is that it doesn't say how confident or structured the classification answer is when multiple rules could apply.

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, front-loaded with the core question and then the mechanism and sourcing. The mid-sentence parenthetical listing s17(2) categories makes the first sentence long, but it earns its place by showing the input-VAT scope concretely.

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, and the description compensates by telling the agent what comes back: a classification grounded in a rules table with the governing VAT Act section, optional related official material, and an explicit no-match statement. For a three-parameter read-only classifier, nothing needed to call or interpret it 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 coverage is 100%, with side and include_library fully documented including the default, so the schema carries most of the weight. The description adds only indirect meaning: the s17(2) list signals what the purchase side covers, and "related official material from the GetLawED library" clarifies what include_library actually retrieves. 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 opens with the exact question answered (standard-rated / zero-rated / exempt, plus input-VAT claimability), naming the VAT Act and the s17(2) denial categories. That verb-plus-resource framing separates it cleanly from the sibling sa_vat_calculate, which computes amounts rather than classifying a supply.

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?

It gives concrete triggering examples ("client lunch at a restaurant", "club subscriptions", "motor cars") and the two angles — output treatment vs input claim — that map to the side parameter. It does not, however, explicitly name sa_vat_calculate as the tool to use once classification is known, so the routing between siblings is left implicit.

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