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

Goes well beyond the readOnly/openWorld/idempotent annotations: discloses that there is no $ floor unlike the app, that data begins when Moby started tracking the token, that duplicate whale+KOL identities are collapsed to one row, that pagination is cursor-based with no gaps or duplicates, and that SELL rows carry held_seconds/quick_flip. These are exactly the non-obvious traits an agent needs before trusting the rows.

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 feed is and its main exclusion, and nearly every sentence contributes a distinct fact. It is dense and long, with a couple of sentences (win_rate/realized_pnl, days_since_prev_trade) that could be tightened, but little is wasted.

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?

An output schema exists, yet the description still explains the interpretation-critical return fields (identities, is_whale/is_kol, win_rate, held_seconds, quick_flip) and the sort/ordering rule. Nothing an agent needs to call this correctly or read the response is missing.

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 60% and the description compensates for the key gap by explaining cursor semantics ('Pass next_cursor back as cursor for the next page until it is null'), which the schema only partly states. It adds no meaning for page, limit or the fixed-value network parameter, so it does not fully close the remaining coverage gap.

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?

States a specific verb and resource — a trade-by-trade feed of tracked wallets that traded one token — and immediately scopes it ('only wallets Moby tracks appear'). It also distinguishes itself from the get_my_* family and from a whole-market feed in the same breath, so an agent can place it among ~60 siblings.

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?

Explicitly says when NOT to use it: it is not the whole market (only tracked wallets) and not user data, with the naming rule 'get_my_ tools return the user's own data' as a routing heuristic. It does not, however, name the closest token-level siblings (e.g. get_token_smart_money, get_whalewatch_feed) and say which to pick, which keeps it short of a 5.

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