Create a split rule

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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description goes well beyond them by explaining that live mode moves real money, that the action cannot be undone, and that the split is frozen onto each payment at creation time. That freezing rule is non-obvious behavioral context an agent could not infer from the schema or annotations.

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?

The safety warning is front-loaded in the final sentence and every sentence carries information. Minor waste: the opening line "Create a split rule" duplicates the title, and the second sentence restarts with the same phrase rather than continuing the thought.

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 destructive, nested-parameter mutation tool with no output schema, the description covers the economics, the units, the downstream wiring, and the safety requirement. It stops short of saying what the call returns (the new rule id, presumably) or what constraints apply to `name`, which matters given there's no output schema to fall back on.

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?

With schema description coverage at only 20%, the description carries real weight and delivers the important part: that `percentage` shares are basis points (2500 = 25%), that `flat` shares are in kobo, and that flat shares are capped at the net amount. It does not explain `name` or `metadata`, and it never mentions `idempotency_key`, so the less obvious parameters are left to the schema.

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 split rule") and immediately defines the resource's semantics: it shares each payment's net amount after fees with subaccounts while the remainder stays in the creator's balance. The create verb also separates it cleanly from the list/get/update split-rule siblings in the tool list.

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?

It gives concrete downstream usage: pass the rule id as `split` when creating a payment, checkout session, payment link, invoice or subscription, and it warns to confirm amount and destination with the user before calling in live mode. What's missing is explicit guidance on when to use `update_split_rule` instead of creating a new rule, or whether multiple rules may coexist.

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