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

With readOnly/idempotent/openWorld hints already present, the description still adds context annotations cannot convey: a $0.05 USDC-on-Base x402 payment requirement, the temporal boundary (since the first Base fill), and the data-gap convention that suppressed weeks return only a reason. It stops short of describing response shape or ordering, which matters given there is no output schema.

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 with no filler; the scope statement leads and the operational caveats (withheld weeks, cost) follow. Density is high, but 'raw Peer onchain oracle at each fill's signal block' is opaque jargon that may cost an agent comprehension even while it saves tokens.

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?

The payment gate, temporal coverage, and withheld-week behavior are covered, but with no output schema the description should say what a weekly rate record looks like (fields, units of the premium, how a withheld week is represented beyond 'the reason'). For a paid, paid-per-call dataset tool that gap is meaningful.

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 50%: platform is documented in-schema but currency carries only a pattern. The description compensates by clarifying currency semantics ('one currency') and, more valuably, that omitting platform aggregates across platforms while supplying it narrows to a single route. It does not confirm the three-letter ISO-code format implied by ^[A-Za-z]{3}$.

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 precise resource: weekly realised seller premiums benchmarked against the raw Peer onchain oracle at each fill's signal block, scoped by currency and optional platform. The domain specificity alone separates it from peerlytics_liquidity_depth, though no sibling is named and no explicit verb (e.g. 'returns'/'lists') fronts the sentence.

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?

The clause 'for one currency across platforms, or one platform route' implicitly tells the agent how to choose between omitting or supplying the platform filter, which is real guidance at the call level. However, there is nothing about when to prefer this tool over peerlytics_liquidity_depth or peerlytics_paid_datasets, and no stated prerequisites beyond the cost disclosure.

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