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

readOnlyHint=false is consistent with a mark-as-read mutation, and the description goes beyond the annotation by disclosing the two-phase SIWx authentication requirement and stating 'No payment is authorized,' which prevents an agent from assuming a cost. It omits idempotency, cursor-staleness behavior, and error outcomes.

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 front-loaded sentences with no filler, and the sequencing instructions appear in call order. Slightly dense with three distinct ideas packed without visual separation, but nothing is wasted.

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 nested-object, zero-coverage, no-output-schema tool, the description covers the auth flow and cursor semantics adequately but leaves new_proof, required-vs-optional status of proof/arguments, idempotency, and cursor-overrun behavior unspecified.

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 proof, arguments, and new_proof, so the description must carry the load. It does map 'arguments: cursor (integer) and optional private_cursor' and ties proof to the challenge flow, but leaves new_proof entirely unexplained and gives no format detail for the proof object.

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?

Specific verb+resource ('Mark notices already served by referral_notices as read up to a cursor') and it explicitly anchors the resource to the sibling tool that produced it, so the agent can separate acknowledge from notices without opening a schema.

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?

It gives the exact two-call flow: call without proof to obtain a SIWx challenge, sign with the referrer wallet, then call again with proof. That is strong operational context, though it never states when not to use this tool or what happens if the flow is abandoned.

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