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

Beyond readOnlyHint=false, the description discloses the two-step challenge/proof handshake, the wallet-signing requirement, and a safety caveat ('No payment is authorized'). This explains why a conceptually 'read' tool can carry a non-read-only annotation, since issuing a challenge can persist state. It omits output shape and failure modes, but no output schema exists to cover those either.

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, front-loaded with what is read, then the auth procedure, then the payment caveat. It is appropriately sized for the tool's complexity, with only the 'arguments: none' phrasing wasting or muddying space.

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?

Covers the read result and the authentication handshake, and enumerates returned fields in lieu of an output schema. It still leaves gaps for a tool with three nested-object params: the role of new_proof, the contents of the proof object, and any error/permission behavior are unaddressed.

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% across three nested-object parameters, so the schema carries no semantics at all. The description explains the 'proof' flow (call without, then with proof) but leaves 'new_proof' entirely unexplained, and its statement 'arguments: none' actively conflicts with the presence of an 'arguments' property in 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?

States a specific verb ('Read') and resource (a registered referrer's code, referral link, accepted vs. current terms, action-required flag), so an agent knows exactly what it returns. It is naturally distinguishable from write-oriented siblings like referral_accept_terms and referral_register, though it never names them explicitly.

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 concrete invocation instructions: no arguments needed, call without proof to receive a SIWx challenge, sign with the referrer wallet, then call again with proof. That is real procedural context and a clear when/how-to-call. It does not, however, contrast with alternatives such as referral_notices or referral_program.

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