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

Adds real behavioral context beyond the annotations: 'Nothing is charged by this tool itself', that the URL is human-opened rather than API-consumed, the never-a-second-checkout guarantee, and white-label visibility. This usefully complements readOnlyHint=false and destructiveHint=false, which alone would not explain the money/side-effect profile. It stops short of detailing auth requirements or link expiry.

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-loads the single most important fact (a URL a human opens) before the mode branching. Somewhat parenthetical-dense and could trim, but every clause carries distinct information.

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?

No output schema exists, and the description covers what is returned (a URL), both branches, the side-effect guarantee, and a visibility caveat. For a two-parameter tool this is complete.

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%, so baseline would be 3, but the description adds semantics the schema only lightly implies: the origin of planId ('from get_billing plans') and the conditional runtime branching that changes what the parameter actually does depending on subscription state.

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 return value ('Returns a URL a HUMAN opens in the browser') and cleanly separates the two operating modes: billing portal without planId vs Stripe Checkout with planId. An agent can distinguish this from get_billing and get_plan without opening either 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?

Explicitly conditions each mode ('Without planId…', 'With planId (from get_billing plans)…') and names the sibling that supplies planId. It even handles the tricky case (an existing live subscription gets the portal link, 'never a second checkout') and warns it is hidden for white-label customers.

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