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

Beyond the annotations (readOnlyHint=false, idempotentHint=true), the description discloses a state machine: immediate confirmation when the caller is the receiver, pending status when the caller is the payer, visibility in net_pending_minor only, and the double-count hazard. This is exactly the behavioral context an agent needs before calling.

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 core action is front-loaded and most sentences earn their place. The final sentence about the inbox/confirm_payment case is dense and slightly convoluted, but it conveys a hazard that is worth the words.

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?

An output schema exists, so return values need not be explained, and the mutation/idempotency profile is covered. Remaining gaps are minor: no statement of permission requirements and no guidance on the optional note/occurred_at fields.

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 description coverage is only 14% (only idempotency_key documented), so the description carries most of the burden. It usefully explains that `from` defaults to the caller and that `amount` is denominated in the group currency, but it says nothing about `note`, `occurred_at`, or accepted identifier forms for `to`/`from`.

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?

The description states a specific verb and resource ('Record that money changed hands outside splitsi, from one member to another, in the group currency') and scopes the operation to off-platform payments. It is immediately distinguishable from confirm_payment and add_expense.

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 explicitly routes the agent: use confirm_payment when the counterparty already recorded the payment and an inbox item asks to confirm it, because recording again double-counts. It also states the outcome depends on whether the caller is the payer or the receiver, which changes the workflow.

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