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

Annotations already cover the safety profile (readOnly, non-destructive, non-idempotent, open world), and the description adds real behavioral context: sort order (timestamp then ingestion `sequence`), null semantics for unknown values, and the fact that filtering rejects unrecognised enum values instead of silently dropping them. It does not discuss pagination depth/limits or rate/cost, so it stops short of full transparency.

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 purpose and filters, but the 'this is public market data, not the user's own wallet' caveat appears twice (in the ⚠️ warning and again in the closing paragraph), and the long per-field `context` enumeration largely duplicates the output schema. Dense and useful, but padded beyond what an agent needs to select and call the 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 an 11-parameter, zero-required filtering tool, the description plus a 91%-covered schema and an output schema leaves nothing blocking a correct call: scope, filter sources, sort order, null handling, and cross-tool routing are all covered.

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 91%, so the baseline is 3; the description earns above that by disambiguating the riskiest parameter (`wallet_address` = tracked whale, not the user) and pointing `list_ids` at its source tool. It expands `include_context` into the concrete fields returned. `transaction_types`, `min_days_since_prev_trade` and the timestamp filters are left to the schema.

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 — buys and sells by tracked whale wallets across the market, newest first — and immediately scopes it against siblings (get_my_activity for the user's own trades, get_whalewatch_feed_window for bulk time windows). An agent can distinguish this from get_whalewatch_home_feed/get_whalewatch_kol_feed only indirectly, but the core resource is unambiguous.

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 names alternatives and the condition that selects each: get_my_activity for the user's own trades, get_whalewatch_feed_window for a bulk read of a whole window, get_whalewatch_lists to obtain list_ids, get_whale_wallet_track_record for wallet quality. It also carries a hard 'when-not' warning about `wallet_address` not being the user's wallet.

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