l402-reconcile

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

Annotations only provide openWorldHint=true and destructiveHint=false, but the description adds substantial behavioral detail: auto-pay to the service is paused while unresolved, settled payments store credentials when possible, failed payments are cleared, and abandon requires human approval. This is far beyond what the annotations alone 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 a single dense paragraph with the core purpose front-loaded, followed by invocation modes and parameter-specific behavior. Every sentence earns its place; there is no filler or repetition of schema details.

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?

Given three optional parameters, no output schema, and significant side effects, the description covers invocation modes, resolution outcomes, credential storage, and the human-in-the-loop requirement. It does not describe the return format of listing unresolved payments, but this is a minor gap for an agent already given the schema.

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%, but the description adds real meaning beyond the schema: paymentHash triggers an NWC lookup_invoice or Cashu mint lookup, preimage must hash to the payment hash to settle, and abandon requires human confirmation. It enriches each parameter with behavioral context rather than repeating schema text.

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 states a specific verb and resource: 'Resolve a payment whose outcome is unknown' and immediately distinguishes the two main modes: listing unresolved payments versus resolving a specific one. This clearly separates it from siblings like l402-pay or l402-fetch by focusing on reconciliation of uncertain payments.

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 call patterns: call with no arguments to list, with paymentHash to query the wallet, with preimage to settle, or with abandon for human confirmation. It does not explicitly name sibling alternatives or state when not to use the tool, but the usage conditions are clear enough for an agent.

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