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

Annotations only declare non-read-only, open-world, non-destructive; the description adds the material behavior: owner-only authorization with sign-in required, that the link is private, that sensitive data flows directly to a third party outside the chat, and that returning from onboarding is not proof the account is ready. That last caveat is exactly the kind of post-condition an agent would otherwise get wrong.

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 short sentences, front-loaded with the authorization gate ('Owners only (needs sign-in)') before the trigger and the behavioral constraints. Every sentence carries distinct, actionable information with no restatement of the name or title.

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, yet the description tells the agent what is produced (a private Stripe-hosted onboarding link) and how to verify state afterward via receptionist_service. For a zero-parameter, single-effect tool, nothing needed to invoke it correctly is missing.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline for a 0-param tool applies. The description correctly conveys that business, bank and identity data are collected by Stripe rather than passed as arguments, which is the only parameter-adjacent fact that matters here.

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 artifact — 'create a private Stripe-hosted onboarding link' — scoped to 'when the owner asks to accept customer payments'. It also names the sibling tool (receptionist_service) used for the follow-up check, so an agent can tell this apart from status/verification tools without opening a 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 an explicit trigger condition ('when the owner asks to accept customer payments'), an explicit exclusionary behavior ('Do not ask for these details in chat'), and an explicit next step via an alternative tool ('check receptionist_service after refresh'). When-to-use, what-not-to-do, and what to do afterward are all covered.

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