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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals the human-in-the-loop nature, the destructive drain of the relay mailbox on the paired receive call, that the dpop_token must be persisted by the caller (the MCP does not retain it across restarts), and that proof expires after the patron's chosen duration. This is rich, actionable behavioral context beyond a simple mutation alert.

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?

Although longer than a one-liner, the description is tightly segmented: a one-sentence summary, flow trigger, human-in-the-loop warning, explicit after-steps, return contract, and lifecycle. Each paragraph serves a distinct operational purpose and is front-loaded with the core action; there is no filler.

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?

The description fully covers the trigger condition, the follow-up with a sibling tool, the step-by-step user interaction, the destructive-receive caution, the dpop_token handling, and expiration lifecycle. An agent has all the context necessary to call this tool correctly and sequence it with receive_npub_proof.

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?

The input schema has 100% description coverage for all three parameters, so the schema already explains reason, verify_at, and patron_npub. The tool description does not add parameter-specific meaning beyond what the schema covers, so it meets the baseline without exceeding it.

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 opening sentence names the verb, resource, and channel: 'Request npub ownership proof from a patron via Nostr DM.' It also explicitly differentiates from a sibling by stating what it does NOT deliver ('does NOT deliver any service secret') and points to request_credential_channel for secrets, making the purpose unambiguous.

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 an exact trigger condition ('use it when a call returns proof_required'), names the alternative for secrets, and provides explicit post-call sequencing: STOP, tell the user to check Nostr, wait for confirmation, then call receive_npub_proof. It also warns against polling/retrying and gives lifecycle timing, leaving no ambiguity about when to invoke it.

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