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

Annotations only say non-readOnly, non-destructive, closed-world; the description adds substantial behavior beyond that — idempotency semantics (same key returns the original order, no second charge), what success returns (order_id, status, credits_used), payment-rail rules (PRO credits beat stripe_link, STRIPE_LINK_DISABLED has no silent fallback), and explicit display prohibitions (never show checkout_hash, only payment_link/order_id). This is exactly the mutation-context an agent needs.

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 core action and routing rule, then layered with operational constraints. It is dense and slightly sprawling in the middle (payment-gateway warning, display rules, account linking), but nearly every clause carries a decision the agent must make.

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 12-parameter mutation tool with an output schema, this covers the remaining gaps: vertical inference, guest vs PRO flow, retry/ambiguity handling, multi-SKU behavior, and display constraints. Nothing essential to calling it correctly is left unstated.

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 already 92%, so the baseline is 3. The description still adds real value on top: price_token only for gift cards with no phone and no country_id, and a distinct idempotency_key per SKU — cross-field constraints the schema documents per-property but not jointly.

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 a specific verb+resource ('Place the order') and immediately clarifies scope: one tool covering every vertical, with `type` inferred from price_token/catalog_id. An agent can tell what it does and how vertical routing works 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?

Gives concrete when-to-call guidance: guest/consumer calls as soon as the product is chosen (preview optional), OAuth PRO must preview first with the same body. It also covers multi-SKU (N calls, distinct idempotency keys) and the ambiguity fallback to list_orders/get_order_status. It stops short of naming the sibling tools it overlaps with (create_esim_order, create_esim_topup, preview_order), so the agent must infer why those exist alongside this one.

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