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

With annotations already carrying idempotentHint=false and destructiveHint=false, the description adds substantial value beyond them: it states the write behavior ('mints a cart'), discloses the concrete auth failure signature (JSON-RPC error -32001 with data.code=MCP_API_KEY_REQUIRED) and that the call 'never reaches the tool' without a key. This contextualizes real-world failure behavior that annotations cannot express. No contradiction with annotations — 'mints a cart' is consistent with readOnlyHint=false.

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 tight paragraphs with the core behavior front-loaded first and auth notes appended second. Every sentence earns its place, though the auth paragraph is slightly long-winded (three sentences covering the error, the key request path, and the read-tier contrast) and could be trimmed without losing signal.

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 high-complexity tool — 7 parameters, a nested buyer object, no output schema, and 0% schema descriptions — the description covers the output contract (hosted URL vs. client_secret) and auth, which is good since there's no output schema. But it leaves five parameters unexplained and gives no guidance on `returnUrl` or the buyer requirements. The half that is covered is strong; the parameter-semantics half is a clear gap.

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 0%, so the description bears the full burden of explaining parameters. It does explain `mode` thoroughly (hosted vs. managed semantics and default) and implies `skuId` via 'SKU'. But `shopId`, `quantity`, `buyer` (a nested object whose `email` is required), `returnUrl`, and `paymentMethod` receive no explanation, leaving an agent to guess their meaning from names alone. Partial compensation only.

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 precise verb-resource pairing ('Begin an agent-initiated droplinked checkout for a SKU') and immediately clarifies the mechanism ('Mints a cart on droplinked-backend') plus the two distinct return modes (hosted URL vs. Stripe client_secret). It even names the default behavior. This fully distinguishes it from cart.* editing tools and process_payment.

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?

The description explains the hosted vs. managed mode distinction and clarifies the authentication context: it's not on the public read tier, returns a specific JSON-RPC error without a key, and contrasts with discovery/catalogue/trust-fabric reads that need no credential. It does not, however, explicitly route agents away from sibling tools such as process_payment or cart.addLine in a given scenario, which prevents a 5.

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