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

Annotations only declare readOnlyHint=false; the description adds real context beyond that — the two-step challenge/sign handshake, oldest-first ordering, and the explicit 'No payment is authorized' note. It still does not explain what side effect makes the call non-read-only, leaving a small tension with readOnlyHint=false.

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?

Three tight sentences: purpose first, then arguments, then the auth flow, with zero filler. The parameter hints are packed inline rather than padded out.

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 paginated, auth-gated read with no output schema and 0% schema description coverage, it covers ordering, pagination args, and the auth sequence adequately. What a receipt contains and the purpose of new_proof remain unstated.

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% and all three params are undescribed nested objects, so the description carries the burden. It documents 'arguments' (optional cursor, limit 1-50) and the role of 'proof', but never explains 'new_proof' or the nested shapes — partial compensation only.

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 ('Page through a referrer's commission receipts') plus ordering ('oldest first'), which separates it from siblings like referral_status or referral_notices. It never explicitly names an alternative tool, so it sits just short of a 5.

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 a concrete calling protocol: call without proof to obtain a SIWx challenge, sign with the referrer wallet, then call again with proof, and notes payment is not required. It does not, however, say when to prefer this tool over the other referral_* siblings.

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