sign_and_pay

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

With no annotations, the description carries the full burden and does most of it: it discloses that real value moves on-chain, names the returned fields (payment_signature, settlement_tx), states what is deliberately omitted (VPN credentials), and warns about double charging. It stops short of covering failure/retry behavior, wallet prerequisites, or what dry_run actually changes — material gaps for an irreversible money-moving call.

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?

Three sentences, front-loaded with the 'DEBUG ONLY' warning, then the capability, then the mandatory next step. Every clause carries operational consequence; nothing is redundant.

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 no-annotation, no-output-schema, money-moving tool the description does well on return values and workflow ordering. But it never explains the required accepts payload or dry_run, so an agent still lacks what it needs to construct a correct call in this deliberately dangerous path.

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 0% and the required `accepts` parameter is a nested array of objects with seven required subfields. The description only implicitly touches `invoiceNo` (via the fulfill_payment matching requirement) and is silent on `dry_run`, `network`, and the entire accepts structure, leaving an agent to guess at payment-critical fields.

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?

States a specific verb and resource ('Broadcasts on-chain payment') and immediately bounds scope with 'does NOT fetch VPN credentials'. It distinguishes itself from siblings by naming buy_vpn and fulfill_payment, so an agent can place it in the workflow without opening any schema.

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?

Explicit exclusions ('Prefer buy_vpn', 'DEBUG ONLY') plus a hard mandatory follow-up ('you MUST next call fulfill_payment with the same invoice_no') and a named failure mode ('double charge'). The when-not, the alternative, and the cost of getting it wrong are all stated.

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