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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered; the description instead adds genuinely new context about the payout mechanics behind the numbers (USDC on Base, weekly batches, $5 minimum, capped, admin-approved, sent to your payout address). That explains what the pending/unpaid/paid fields mean, which the schema cannot. It stops short of saying whether the stats are time-scoped or lifetime, which matters for a zero-parameter call.

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?

Two sentences, front-loaded with the returned fields before the payout caveats, with no filler. The first sentence is a dense comma list that reads slightly like a schema dump, but every item is informative.

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?

With no output schema and zero parameters, the description carries the return-value burden and does it reasonably well by enumerating the metrics. The one real gap is scope – nothing says whether the numbers are lifetime or windowed, which an agent would need to describe results accurately.

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 no parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. The enumerated field list is a bonus rather than a substitute for parameter documentation.

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?

Names the resource precisely and enumerates exactly what the dashboard returns (clicks, referred users, sales, USD breakdowns, recent sales/payouts), so an agent can tell it apart from get_referral_link or get_balance without opening anything. It lacks an explicit verb and never names the sibling it is distinct from, keeping it 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?

Usage is only implied by the noun phrase 'Referral dashboard' – the agent must infer that this is the read call for referral performance. No when-to-use conditions, no exclusions, and no pointer to get_referral_link for the invite URL or set_payout_address for changing the payout destination.

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