Post Instances Customers Bank Accounts

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

Annotations confirm this is a non-read-only, non-destructive, non-idempotent, open-world write; the description adds genuinely new behavior: required fields are rail- and country-dependent, validation should be derived from a live bank-details call, and some rails are blocked for light-KYC customers. It stops short of describing the created resource (e.g. that the account starts in a verifying status) or failure modes.

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 the one-sentence purpose, then prerequisites, then per-rail constraints. The long country enumerations are verbose but each carries real conditional logic that cannot be inferred. Slight density cost, no filler sentences.

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 tool with a very large nested requestBody and no output schema, the description's strategy of delegating the exact field list to the bank-details endpoint is a sound coping mechanism, and the conditional requirements cover the most failure-prone inputs. The remaining gap is the response shape and what state the new account lands in, which nothing else in the definition supplies.

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 ~50%, and the description compensates with the highest-value semantics the schema lacks: `type` is the rail that determines the rest of the body, `business_industry` must be a NAICS code required for business account_class, `phone_number` and `tax_id` are country-conditional, and US `state_province_region` must be two letters. It does not touch instance_id/customer_id, but those are self-evident from names and examples.

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?

"Adds a payout destination for a customer" names a specific verb (adds) and resource (payout destination / bank account) and makes the effect on the customer record clear. It does not, however, distinguish the tool from the sibling PostV1InstancesCustomersBankAccountsPlaid, which also attaches a bank account, so the agent has no textual basis for choosing between 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?

Gives strong conditional routing: call GET /v1/available/bank-details with the rail first to get the exact field list, and pull NAICS codes from GET /v1/available/naics. It also states an explicit exclusion — ach, wire and rtp are unavailable for light KYC customers. Missing only guidance on when to prefer this over the Plaid-based sibling.

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