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

Annotations only flag destructive/openWorld/non-idempotent; the description adds substantial behavioral detail beyond that: every call requires an X-Wever-Wallet-Proof bound to the exact request body, attribution rejects self-referrals and permits only the first code, claims reserve earnings and create a linked payout instruction, claim_id must be stable for retries, amounts are bounded 1.00–25.00 USDC, outstanding accruals cap at 200.00 USDC and fail closed, plus the shared 100 USDC/day payout cap and paid-URL pricing. That is exactly the kind of mutation/auth/limit context annotations cannot convey.

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 action list is front-loaded, which is good, but the remainder is a dense wall of long sentences mixing auth, economics, caps, retry semantics, and pricing without any structural separation. Every clause is informative, yet the sheer density and lack of chunking make it harder to scan than it needs to be.

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 multi-action payment tool with no output schema and a oneOf schema, the description covers authentication, action semantics, amount bounds, retry/reconciliation flow, caps, and where to find the full contract (402 body, /api/referral-contract). It is close to complete; minor gaps remain around what the earnings/receipt responses actually contain, though the signed-receipt guarantee is stated.

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 already 100%, so the baseline is 3, but the description adds real meaning: amount_usdc is optional and requests an exact amount within the available balance (omit to take the balance up to 25 USDC), and claim_id is required to be stable across retries. It also explains the role of code_token (signed, binds attribution) beyond the raw type/pattern constraints.

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 first sentence enumerates all five operations with specific verbs and resources (create rail-signed code, attribute wallet with code_token, inspect earnings, claim USDC, verify receipt), so an agent can map an intent to the correct action without opening the schema. It also names the sibling payout tools (wever_payout-authorize / wever_payout-execute) used by the treasury holder, differentiating itself from those.

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 selection conditions: omit amount_usdc to claim the available balance, supply it for an exact amount within the available balance; retry the original claim after execution to reconcile; the treasury holder should use wever_payout-authorize/execute instead. It stops short of explicitly stating when NOT to use this tool versus other rails (e.g., subscription-rail, payout-create), so it is clear context without full exclusions.

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