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

With no annotations, the description carries the full load and does most of it: read-only ('Reads only; you keep your keys'), freshness (refreshed every 2 minutes), price ($0.02 per call) and accepted payment rails (USDC on Arc/Base/Solana, XNT on X1). It does not cover failure modes — what happens on an invalid or expired payment signature, or whether a failed second call is still billed — which matters for a paid tool.

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 what the data is, then cadence, then cost, then the payment procedure — the order an agent needs it. Every clause carries information; even the 'Not advice' disclaimer is short and load-bearing for a trading-signal tool.

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 single-parameter paid read with no output schema, it discloses contents (size, time, wallet record, simulated sell check), freshness, price, rails, and the payment handshake — enough to call correctly. The only substantive gap is error behavior and whether the simulated sell check is sometimes absent, which it hints at with 'where we have one' but does not explain.

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 already 100%, so the baseline would be 3, but the description adds meaning the schema cannot: the discovery call without `payment` returns terms that must then be signed, and the signed payload is what completes the purchase inside the same call. That workflow is not inferable from the schema's one-line param description.

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 first sentence names a concrete verb and resource — 'newest buys by the 25 most profitable wallets of the last 24 h' — and pairs it with the use case ('copy-trade signals'). An agent can tell this apart from generic siblings like arc_whales or arc_trades without opening any schema, since it states the cohort, window and cadence.

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 an explicit two-call protocol: call once without `payment` for the terms, sign with your own wallet, call again with `payment`. That is real when/how guidance. What it lacks is routing relative to siblings — nothing says when to prefer arc_whales or arc_trades over this paid feed, or when a paid call is unnecessary.

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