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

With no annotations, the description carries the full burden and discharges much of it: it discloses the 1% platform fee with rounding and minimum, gives the exact response field (platform_fee_sats), and flags the 'REQUIRES AGENT KEY' authorization prerequisite. It omits that the transfer is irreversible once sent and does not say whether the amount is drawn against a spend policy or budget, both material for a payment 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 compact sentences with the core action first, then cost, then the auth prerequisite — the most decision-relevant facts front-loaded. No filler or redundant restatement of the tool name.

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?

With no output schema, naming platform_fee_sats is a real contribution, and the auth requirement covers the main gating condition for a 3-parameter payment tool. What remains missing is failure behavior (invalid destination key, insufficient balance) and the irreversibility of the transfer, which an agent spending real funds would want 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 description coverage is 100%, so all three parameters are already documented and the baseline is 3. The description adds only marginal semantics — that the 1% fee applies to the amount being sent — and does not clarify message TLV usage or destination key format beyond what the schema states.

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 ('Send a payment directly to a node') and immediately scopes it as 'without an invoice (keysend/spontaneous payment)', which cleanly separates it from siblings like pay_invoice, pay_lightning_address and pay_l402_api without needing to name them.

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 'without an invoice' framing tells the agent exactly which condition selects this tool over the invoice-based payment siblings. It stops short of an explicit 'use pay_invoice when you have a BOLT11 invoice' exclusion and says nothing about preconditions such as holding sufficient balance, so usage context is clear but not fully routed.

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