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

With annotations present the bar is lower, and the description does add real context: 0.10 USDC per call on Base, 10 signed-wallet free calls per rolling 30 days, and a pointer to the 402 body for x402 terms. It does not reconcile the sharp tension between the 'viewer'/'retrieve retained result' framing and destructiveHint=true, leaving the agent unsure whether records or credits are consumed.

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?

It is a single run-on paragraph that leads with pricing rather than purpose, then mixes the operating boundary, the HTTP route, credential disclaimers, and a link to /api/operations-contract. Several clauses ('This adapter grants no authority and never supplies server credentials', 'Wallet-authenticated bounded operations service with durable records') are boilerplate that do not help an agent invoke the tool.

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 two-parameter tool with a nested oneOf discriminator, no output schema, and 0% schema description coverage, the description should explain the two retrieval branches and what evidence comes back. Instead it misdescribes the input as a computation ID and only vaguely says the response includes 'record status and available evidence'.

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 0%, so the description must carry the input semantics and it does not. It instructs the caller to 'provide the completed computation ID', but the schema accepts no computation ID at all — only mode='retrieve' plus a work object that is either wallet_free_call with a hex nonce or settled_payment with a 64-hex payment_id. The critical fork between the free-call and paid-payment retrieval paths is never mentioned.

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 opening sentence states a specific verb and resource: retrieve a wallet-owned completed Wever computation from durable billing records, including its exact result and verified digest. That is concrete enough to act on, but it never distinguishes this from adjacent siblings such as wever_proof-inbox, wever_receipt-passport, or wever_purchase-status, which plausibly return overlapping evidence.

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?

The 'Operating boundary' sentence gives a usable precondition (supply the completed computation identifier from your wallet), and the pricing line hints this is a metered lookup. However, no when-not guidance, no named alternative, and no statement of which upstream tool produced the record being retrieved.

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