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

With no annotations, the description bears the full burden of behavioral disclosure, and it delivers richly. It explains that the tool sends a welcome DM with a credential template, that the flow is human-in-the-loop, that the recipient must reply manually, and that receive_credentials destructively drains the relay mailbox and must not be retried. These are precisely the behavioral facts an agent needs.

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 longer than typical, but every sentence earns its place: summary, flow classification, sibling distinction, OAuth2 caveat, human-in-the-loop warning, and post-call sequencing. Key warnings are front-loaded and bolded, making the critical constraints hard to miss. This is well-structured despite its length.

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 tool embedded in a delicate human-in-the-loop workflow with a destructive downstream call, the description is complete. It covers the tool's action, when to use it, when not to use it, what happens after, and how the agent should sequence subsequent steps, including stopping and waiting for user confirmation. The presence of an output schema means return-value documentation is not the description's job.

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 already provides 100% description coverage for both parameters, describing service as the credential service name and sender_npub as the npub to send the template to. The description adds useful context about the overall credential-delivery domain, but it does not add meaningfully new per-parameter semantics beyond what the schema already states. Baseline 3 is appropriate.

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 opens with a specific verb and resource: "Open a Secure Courier channel for credential delivery." It clearly identifies the tool's purpose as handing over service secrets (API keys, tokens), and explicitly differentiates it from request_npub_proof, which is a distinct proof-of-control flow. This leaves no ambiguity about what the tool does or how it differs from its closest sibling.

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 provides explicit when-to-use guidance: use this for the CREDENTIAL-DELIVERY flow, not for mere npub control, and check service_status first for dynamic/OAuth2 services. It also gives concrete post-call instructions: STOP, inform the user, wait for confirmation, and avoid polling or retrying with receive_credentials. This is exemplary usage guidance.

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