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

Beyond the readOnly/idempotent/closed-world annotations, the description discloses non-obvious behavior: it never raises a protocol error, instead returning {"error": "<what is wrong and how to fix it>"} with a concrete example message, and it states retry is always safe after correction. It also flags the PREMIUM licensing constraint, which annotations do not cover.

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?

The purpose and the exclusion are front-loaded, and the example output JSON earns its space by showing exactly how the two methods diverge. Slightly long overall—the full six-field sample response could be trimmed—but no sentence is filler.

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 two-parameter read-only calculator with a full output schema, the description supplies everything an agent needs: purpose, routing rule, error contract, retry safety, and licensing caveat. Nothing required 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 coverage is 100%, so the baseline is 3; the description goes beyond it by supplying a worked input {"price": 200, "discounts_pct": [20, 10]} that concretely demonstrates that the array order is the application order. Validation bounds are left to the schema (exclusiveMinimum, minItems), which 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 opening line names a specific operation ('stack discounts') and a specific analytical distinction ('sequential vs additive comparison'). It explicitly rules out a sibling ('Not for a single discount inside an invoice (invoice_total)'), so an agent can route between this and invoice_total without opening either 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?

It states the trigger condition directly: 'Use when more than one discount applies and the order changes the answer,' and names the alternative tool for the excluded case. Both the when-to-use and the when-not-to-use are explicit, with the sibling named.

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