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 well: it discloses the on-chain payment prerequisite, the ~20-30s confirmation wait, the one-key-per-address rule, and the single-use constraint on payment transactions. It stops short of describing failure modes or the return value, but the key behavioral gates are all present.

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?

Four sentences, front-loaded with the core action before the procedural detail. Slightly long, but each sentence carries a distinct constraint (payment, timing, uniqueness, reuse) and none is redundant.

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 two-param registration tool with no output schema and no annotations, the description supplies the prerequisites, timing expectations, and failure conditions an agent needs to call it correctly. Only the response shape and error semantics are unaddressed, which is minor here.

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 0%, so the description must compensate. It does: from_address is identified as 'the Cardano address you want your key bound to' and registration_tx as 'that transaction's hash' from the payment. Both parameters gain meaning beyond their bare names.

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 and resource — 'Register a new API key' — and immediately scopes it with 'by paying a one-time fee.' This clearly distinguishes it from siblings like mint or prepare_payment, which involve payment but not key registration.

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 sequences the workflow: pay the fee from the target Cardano address to the operator's payment_address, then call this with the tx hash. Names the sibling tools get_server_info (for the fee/address) and check_payment_status (to verify confirmation), and states exclusions — one key per address, and a payment tx cannot be reused.

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