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

Annotations only declare readOnlyHint=false, openWorldHint=true, destructiveHint=false — they say nothing about money. The description adds the crucial fact that this is a real Stripe session whose payment charges the user's card, plus the confirmation gate. It stops short of stating what happens on an unapproved plan or whether abandoned sessions expire, but the safety-critical disclosure is well beyond what the annotations carry.

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?

Four tight sentences with no filler, and the ChatGPT carve-out plus the getBillingInfo dependency are front-loaded. The most safety-critical sentence ('REAL ACTION... charges the user's card') sits in the middle rather than leading, which slightly weakens front-loading for a card-charging tool.

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 two-parameter mutation with no output schema, the description covers the routing branch, the input source, the real-world consequence, and the confirmation requirement. It omits what the call returns (presumably a checkout URL) and failure behavior for a non-approved plan, which an agent would want before promising an outcome.

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 100% and both parameters already document their constraints (plan ID must come from getBillingInfo; billing period must be user-confirmed). The description reinforces the plan/period/price display requirement but adds no syntax, format, or edge-case detail beyond the schema, so the baseline 3 applies.

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?

States a specific verb and resource: create a hosted Stripe Checkout link for one approved plan and billing period. It also names the sibling that supplies the inputs (getBillingInfo) and the ChatGPT-specific branch, so an agent can distinguish this from the read-only billing tools without opening any 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 explicit when-not (in ChatGPT, checkout is unavailable — return the dashboard link and do not create a session), when-to (other MCP clients, one approved plan/period from getBillingInfo), and a mandatory precondition (show the exact change and get explicit confirmation immediately before calling). Nothing about routing 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.