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

Annotations already declare readOnly, idempotent, and non-destructive, so the safety profile is covered. The description adds behavior beyond them: results are epoch-scoped and refresh every 24h, and claiming is not possible through this tool because signatures happen on the external rewards page. Return shape and pagination are not addressed, keeping it below a 5.

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 and information-dense, but the parenthetical scoring multipliers (1.5x CSPs, 0.2x open interest) are content the tool returns rather than information needed to select or invoke it, and the main sentence is an overloaded run-on. Trimming the multiplier detail would lose no invocation value.

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 one optional parameter, no output schema, and annotations carrying the safety profile, the description covers what the tool returns, the epoch window, and the out-of-band claim path. It leaves the response structure and empty-result behavior unspecified, which is a modest gap for an otherwise simple read.

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 100% and the single parameter already documents "Wallet to look up; omit for the program only." The description restates that split ("for a given address") but adds no format, case-sensitivity, or error semantics for a malformed address. Baseline 3 applies since the schema does the heavy lifting.

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 a concrete resource (USDG trading rewards) and enumerates exactly what comes back: current 24h epoch pool, scoring rules, per-address points and estimated USDG, claimable epochs, and claimed history. No sibling tool covers rewards, so an agent can distinguish it from get_activity, get_positions, or get_staking without opening the 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 makes the address-optional split explicit ("for a given address... omit for the program only") and rules out the claim action: "Claims are signed on the kyte.sh Rewards page." It does not name a sibling alternative for related data (e.g. positions or activity), but the usage context is clear enough to act on.

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