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

With no annotations, the description carries the full burden and does well: it discloses exact costs (0.01 USDC on Base via x402, 12 sats Cashu NUT-24, or 12 sats L402), that validation happens before payment, and the naming/availability rules. It does not describe the success/failure response or whether registration is permanent.

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?

Information-dense but front-loaded: identity and target, then serving path, then name rules, then cost/payment options. Each sentence earns its place, though the telegraphic style packs several distinct facts per sentence.

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 paid, unannotated, no-output-schema registration tool, the description covers purpose, constraints, pricing, and payment rails well. The main remaining gap is post-registration behavior (what is returned, reversibility), which no structured field supplies.

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 0%, so the description must compensate, and it does: it explains name syntax (a-z0-9._-, max 30), pubkey type (hex), and relays format (optional, comma-separated wss:// URLs). This meaningfully fills the schema gap for all three parameters.

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 (Registers) and resource (Nostr NIP-05 identity name@domain for a hex pubkey), and names the serving location (/.well-known/nostr.json). No sibling tool overlaps, but the purpose is unmistakable and self-contained.

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 clear operating context: name constraints, first-come-first-served, and that invalid/taken names are refused before payment. It also routes the agent to the free availability check (/nip05/check?name=) as an alternative pre-step, though it stops short of explicit when-not guidance.

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