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

With no annotations provided, the description carries the full burden. It discloses key behaviors: sends a welcome DM, requires human-in-the-loop action, and warns that `receive_credentials` destructively drains the relay mailbox. It also explicitly says not to poll or retry, providing actionable transparency.

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 multi-paragraph but every sentence earns its place: the first line gives the core purpose, later lines add critical alternatives, behavioral flow, and operational warnings. Formatting with bold and line breaks improves readability without waste.

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?

Despite having an output schema, the description goes beyond structured data to explain the human-in-the-loop workflow, the need to wait for user confirmation, and the destructive nature of the downstream receive call. This level of context is complete for a tool with such operational nuance.

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% with both parameters already described in the input schema. The description does not add new parameter-level meaning beyond the schema, so the baseline score of 3 is appropriate. The description mentions the source of the service name (e.g., from onboarding status), which slightly reinforces but does not extend the schema.

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 clearly states the tool's purpose: 'Open a Secure Courier channel for credential delivery.' It uses specific verb+resource and immediately distinguishes itself from the sibling `request_npub_proof`, noting that flow is for proving npub control, not credential delivery. The scope is 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?

Explicitly provides usage guidance: use for delivering service secrets, use `request_npub_proof` instead for npub proof, and check `service_status` for OAuth2 services that need no courier. It also gives step-by-step after-call instructions (stop, inform user, wait for confirmation) and warns against polling or retrying.

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