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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered and this is a pure computation with no side effects to disclose. The description adds the return summary ('final price and effective single-discount equivalent'), which is useful context even though an output schema exists. One caveat it does not disclose is that stacking is capped at two discounts, which matters for a tool pitched as handling 'multiple promotions.'

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?

Four short sentences, front-loaded with the core computation before purpose, inputs, outputs, and cross-reference. Nothing is padded. The closing list_bundles pointer is the weakest sentence and arguably does not earn its place in a calculation tool's description.

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?

Annotations supply the safety profile and an output schema documents the return values, so the description only needs to establish scope, inputs, and intent — all present. The remaining gap is that the two-discount ceiling versus the stated 'multiple promotions' framing is never reconciled, which could mislead an agent about input capacity.

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 three parameters are fully documented in the schema and the baseline is 3. The description's 'Inputs: original price, discount % list' summarizes but adds no format detail beyond the schema, and the word 'list' mildly overstates capacity since additionalProperties is false and only discount_1_pct/discount_2_pct exist. No numeric semantics (percentage vs. fraction, ordering) are added.

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?

States a specific verb and resource: 'Compute the effective discount when stacking multiple promotions,' which pins the scope to stacked discounts rather than a single markdown. That implicitly separates it from siblings like calculate_discount, calculate_percentage, or calculate_markup_margin, though no sibling is named. Clear and unambiguous, but it stops short of explicit sibling differentiation.

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?

Offers scenario context ('promo design or shopping comparisons') and a cross-reference ('See list_bundles for related finance-universal calculators'), so usage is implied rather than stated as a decision rule. There is no when-not guidance and no explicit alternative named for the single-discount case. The list_bundles pointer is tangential — it points at a bundle-listing tool rather than a competing calculator.

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