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

With no annotations, the description carries the full burden and does substantial work: it discloses that prices are amount-immutable, that `update_price` only touches active/metadata/nickname, that deletion is unavailable for products/prices/coupons, that a coupon has no `active` flag, and that `expires_at` is rejected when later than the coupon's `redeem_by`. It omits permission/auth requirements and pagination behavior for the list ops, which keeps it below 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?

Front-loaded with the object model and organized into short paragraphs around the immutable-price and coupon/promotion-code distinctions, with warnings marked explicitly. It is on the long side and includes a meta-instruction ('Say that rather than appearing to edit an amount') that reads as prompt scaffolding rather than tool documentation, but there is little true padding.

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 tool with sixteen ops and thirty parameters, the description covers the domain model and the risky mutations well, and an output schema exists so return values need not be documented. However, it never enumerates the ops or explains the eleven list/get operations, and leaves pagination (`limit`, `starting_after`) completely unexplained, so an agent still has gaps for the read paths.

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 77%, so baseline is 3, and the description adds genuine meaning on top: it links `coupon_id` to the coupon-then-code ordering, explains the `expires_at` vs `redeem_by` ordering constraint that the schema only hints at, and clarifies the immutable-price semantics behind `unit_amount`. Parameters like `limit`, `starting_after`, `metadata`, and `amount_off` remain undescribed in both places, so it doesn't fully compensate.

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 the resource domain precisely (products, prices, coupons, promotion codes) and the body makes clear it covers both listing and creation/updating of those objects. It does not, however, state that this is a single multi-op tool with sixteen verbs, nor distinguish it from siblings such as stripe_search or stripe_checkout, so an agent must infer the scope from the schema's `op` enum.

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?

Strong workflow guidance: create the coupon first then the promotion code(s), use `update_promotion_code` with `active=false` instead of deleting, and create a NEW price rather than trying to edit an amount. What is missing is routing guidance against the other Stripe tools (stripe_search, stripe_payment, stripe_checkout) and any hint about the default `list_products` op.

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