Generate one to one hundred cryptographically random RFC 4122 UUID version 4 identifiers.
| Name | Required | Description | Default |
|---|---|---|---|
| count | No | Number of UUIDs. Default 1. | |
| l402_proof | No | L402 payment proof "<macaroon>:<preimage>". Omit on the first call; an unpaid call returns a 0 sat Lightning invoice and the macaroon. Pay the invoice, then repeat the call with this argument set. |
Changes observed during successful MCP inspections.
Input schema / properties / l402_proof / descriptionPrevious value: -"L402 payment proof \"<macaroon>:<preimage>\". Omit on the first call; an unpaid call returns a 5 sat Lightning invoice and the macaroon. Pay the invoice, then repeat the call with this argument set."New value: +"L402 payment proof \"<macaroon>:<preimage>\". Omit on the first call; an unpaid call returns a 0 sat Lightning invoice and the macaroon. Pay the invoice, then repeat the call with this argument set."Input schema / properties / l402_proofAdded value: +{
+ "description": "L402 payment proof \"<macaroon>:<preimage>\". Omit on the first call; an unpaid call returns a 5 sat Lightning invoice and the macaroon. Pay the invoice, then repeat the call with this argument set.",
+ "type": "string"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, so safety is covered. The description adds meaningful detail about cryptographic randomness and UUID version 4. It omits the L402 paid-call flow entirely, which is the one non-obvious behavior an agent would want flagged.
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?
A single front-loaded sentence with no filler; every clause (quantity, randomness, standard, version) carries distinct information.
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 this is mostly sufficient, but a description-only reader would be blindsided by the paywalled first call returning a Lightning invoice instead of UUIDs. The schema covers it, so the gap is not fatal, but the description could have warned about the two-step payment flow.
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 the baseline is 3; the description earns a 4 by restating the count range (one to one hundred) in the call's own intent language and confirming the default of a single identifier is the minimum. It says nothing about l402_proof, though the schema documents that thoroughly.
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 (generate), resource (RFC 4122 UUID version 4 identifiers), quantity range (one to one hundred), and quality guarantee (cryptographically random). An agent knows exactly what it gets and cannot confuse it with hash_generate, which produces digests rather than identifiers.
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?
Usage is only implied by the nature of a UUID generator; there is no explicit when-to-use or when-not, and no pointer to alternatives such as hash_generate for cases where a digest is actually wanted. Acceptable for a narrow utility, but nothing steers the agent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.