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

The annotations provide only readOnlyHint=false and destructiveHint=false, which are vague. The description compensates richly: it discloses the tool is paid, that the probe runs after lease expiry, that verdicts can be 'unresolved' when the probe cannot complete (explicitly never guessed as refuted), and that the raw probe response is published for verification. It also states there is no account or API key required and mentions the feedback channel. This is far beyond what annotations 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 description is long, but it packs necessary information for a complex paid tool: payment flow, probe semantics, verdict outcomes, verification path, and feedback. The first sentence states the core purpose immediately, and each subsequent sentence adds a distinct, non-redundant detail. It is not needle-some, but the length is justified by the tool's complexity. Slightly shorter would be ideal, but it is still well-structured.

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 tool that involves irreversible intent, a lease, a probe, and payment, the description covers all essential aspects: the two-step payment flow, the lease semantics, the probe execution, the three possible verdicts including the honest 'unresolved' case, the raw response publication, and the feedback loop. It references sibling tools (deadman_confirm, deadman_read) appropriately. No output schema exists, but the description tells the user the receipt appears in _meta['x402/payment-response'], which is sufficient. I see no gaps that would prevent correct invocation.

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 100%, so each parameter has a description in the schema (e.g., url, leaseSeconds range, expectedStatus). The main description adds meaning beyond these: it explains the probe is 'GETted from OUR vantage point once the lease expires', that 'At least one of expectedBodyContains / expectedStatus is required' (though the schema also notes this), and how the verdict is determined. It also clarifies the payment-related _meta fields, which are not in the schema but are part of invocation. This enriches the schema without redundancy.

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 opens with a precise verb-object pair: 'register an intent you are about to act on irreversibly, with a lease and a verification probe.' It names the resource (an intent) and the mechanism (lease + probe). It distinguishes from siblings by explicitly mentioning deadman_confirm and deadman_read and by noting it is paid while they are free. This leaves no ambiguity about what the tool does.

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 description gives explicit step-by-step usage: call once without payment to receive a price, then call again with a signed payment in _meta['x402/payment']. It also instructs when to confirm (before the lease expires) and when to read the result (via deadman_read). It clarifies the payment requirement and the flow, leaving no guesswork about when and how to invoke it.

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