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

Annotations already declare a safe, idempotent, closed-world read, so the description is not responsible for the safety profile. It goes further by disclosing domain behavior that governs how to interpret the payload: rewards pay nothing at signup, pay on first event attendance, purchase, or Forge join, after a wait, and are voided by a refund in that window; terms.on false means rewards are paused.

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?

Front-loaded with the resource and its parts, then the payout rules, then the terms caveat. It is dense with semicolons and runs long, but nearly every clause carries interpretable information about the returned fields; only the payout rule sentence could be tightened.

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?

There is no output schema, so the description must carry the return shape, and it does: referral link, referees by first name and initial, gold or paid diamond, pending rewards with pay date, unpaid rewards with reason, plus the terms object and its pause flag. It stops short of stating completeness or ordering of the list, which is a minor gap for a zero-arg personal tool.

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?

The tool takes zero parameters, which is the baseline-4 case. The description correctly adds nothing about inputs and instead spends its words on the shape of what comes back, notably the terms object read from live rules.

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?

The description names the specific resource (the signed-in person's referral link, the referees it produced, and each reward's state) and enumerates the returned concepts, so an agent can distinguish it from my_wallet or my_access. There is no explicit verb, but 'my_referrals' plus the field list makes the retrieval intent unambiguous.

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?

Usage is only implied by the 'my_' naming convention shared with my_wallet, my_profile and my_access; the description never states when to reach for this tool versus those siblings, nor any precondition such as being signed in. It also does not say whether results cover all referrals or only a window.

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