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

Goes well past the annotations: discloses pre-flight OFAC/freeze screening, that failures are atomic (refused before anything is created), and pins each error to a code and HTTP status (payer_blocked, receiver_blocked with details.index, screening_unavailable 503). It also explains output shape and transaction packing against the network limit, which matters for a non-idempotent, open-world write.

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 purpose, then workflow, then errors — a sensible order with no filler sentences. It is a single very dense paragraph with heavy parenthetical nesting, which slightly hurts scannability for such a long body.

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 supplies the return contract (invoices[], transactions[], invoiceIds per transaction) plus the next step for each signature. For a 4-param, non-idempotent, multi-step money-movement tool, an agent has everything needed to call it and recover from each documented failure.

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 only 50% (chainId and the recipients array lack field descriptions), and the description compensates: it ties 'token' to a verified/listed token via token_not_listed, states the 20-wallet cap, and converts recipient rules into actionable errors (batch_duplicate_recipient says to sum amounts into one row, batch_self_payment enforces payer exclusion). Remaining gap is that chainId and the per-recipient memo/amount formatting are only covered in 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?

Opens with a specific verb+resource+scope: pay up to 20 wallets their exact amounts, in the payer's token, on Solana, with an explicit 'no swap' qualifier that separates it from swap_build/swap_quote. The follow-up relationship to payout_report_payment and prepare_signing is named, so an agent can place it in the sibling set immediately.

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 the full activation-to-completion chain: build the batch, sign each transactions[i].transaction via prepare_signing + /v1/svm/execute, then confirm with payout_report_payment. It is clear when to reach for this rather than swap/double/nn builds, but it never states exclusion conditions (e.g. when to use invoice_pay for a single recipient instead).

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