start_purchase

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

With no annotations, the description carries the full burden and does so: 'THIS CALL CHARGES NOTHING', the human must open the URL, 'entitlements attach automatically afterwards', and the 409 product_coming_soon error for architect is disclosed. It also states the agent's own limitation ('you cannot complete a payment, and you should not try').

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 purpose and the critical no-charge fact, and the routing rules sit at the end. The product catalog is long, and the payment caveat is stated twice (once in the opening, once as 'Hand the URL to the user'), a minor redundancy.

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?

A single-enum-param tool with no output schema is fully covered: what it creates and returns, that nothing is charged, the post-payment entitlement flow, the error case, the product catalog with pricing, and pointers to the sibling tools and get_storefront.

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 0% (the enum lists only bare slugs), so the description must supply meaning, and it does: every enum value is explained with price and scope (api base, individual agents at $100/mo, agents-all, roadmap, roadmap-bundle, topups), plus the architect exclusion from the enum. This fully compensates for the schema 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?

Starts with a precise verb+resource+outcome: 'Create a Stripe-hosted checkout URL for one dxpert product and return it.' It immediately differentiates from siblings start_agents_purchase and add_agents by naming the conditions that select them.

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?

Explicit prerequisites and routing: 'Call get_storefront first', 'Use start_agents_purchase instead when the user is subscribing agents to a named site, and add_agents when that site already has a subscription.' It also gives a clear exclusion ('Do not offer to buy' architect). Nothing is left to inference.

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