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

Annotations already declare this a mutating, open-world, non-idempotent operation, so the bar is lower. The description adds genuinely useful context beyond that: 'This tool does not charge anything' discloses that payment is deferred to the Stripe-hosted page, and it clarifies the external flow (buyer redirected to continue_url). No contradiction with annotations — readOnlyHint=false aligns with 'Start a purchase.'

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?

Three sentences, roughly 35 words, with the action front-loaded first and each sentence earning its place: what it does, what to do with the result, and a non-obvious behavioral guarantee (no charge). Zero filler or repetition of schema/annotation content.

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 simple two-parameter tool with no output schema, the description covers the essential return value (continue_url) and the required follow-up action, which is the main thing an agent needs to know. The only notable omission is the semantics of the optional quantity parameter and any failure-mode hints, but neither is critical for a correct first invocation.

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 must compensate; 'one offer' does associate offer_id with the purchase, and the enum values are self-descriptive. However, the quantity parameter is never addressed semantically — nothing clarifies what quantity means (e.g., number of licenses) beyond the schema's default and bounds. The description partially compensates but leaves a real gap.

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 states a specific action ('Start a purchase of one offer') on a clear resource (a Stripe-hosted checkout for an offer) and explains the key deliverable (a continue_url for the buyer). This cleanly separates it from all siblings — get_checkout reads, list_products lists, read_page/search_pages/site_info are informational reads — so an agent can pick it out 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?

The description gives clear usage context: initiate a purchase and send the buyer to the returned continue_url to pay, with the clarifying note that this tool does not charge anything. It stops short of explicitly naming alternatives or when-not-to-use conditions, but the create-vs-read distinction across the sibling set is self-evident and the follow-up workflow is explicit.

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