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

With no annotations, the description carries the full burden and does so richly: it discloses that this is a human-in-the-loop flow, that the receive step destructively drains the relay mailbox (hence no polling), that the returned dpop_token must be retained and passed on every subsequent paid call, that the MCP does not persist it across restarts, and that the tool is free. These are exactly the operational traits an agent cannot infer from schema alone.

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?

Front-loads the purpose and routing rule, then uses bold section headers (Returns, Lifecycle) to organize dense but non-redundant content. Given the multi-step asynchronous human-in-the-loop nature of the flow, every sentence (including the emphasis on MUST/STOP/do-not-poll) earns its place.

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?

An output schema exists, so return values need not be explained, yet the description still surfaces the critical dpop_token contract and retention requirement. Combined with the lifecycle and pairing with receive_npub_proof, an agent has everything needed to invoke this tool correctly and hand off to the next step.

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 the schema already fully documents reason, verify_at, and patron_npub, establishing the baseline of 3. The main description body does not add parameter-level meaning beyond the schema (it only references the dpop_token return value), so no credit above baseline is warranted.

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+resource ('Request npub ownership proof from a patron via Nostr DM') and immediately scopes it against siblings: this is the ownership-proof flow, NOT the secret-delivery flow, and it explicitly names request_credential_channel as the alternative for API keys/OAuth secrets. An agent can distinguish it from receive_npub_proof and request_credential_channel 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?

Gives the triggering condition ('use it when a call returns proof_required'), names the alternative and its distinct purpose, and provides an explicit operational sequence: STOP, tell the user, wait for confirmation, do NOT poll or retry. It also covers the expiry lifecycle and when to re-invoke. Nothing is left to inference.

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