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

Annotations only declare read-only/non-destructive/open-world; the description adds substantial behavior: cursor pagination protocol, stable paging ('new trades never shift a page'), newest-first sort with `timestamp` then `sequence` tiebreaking, the 48h rejection, null-value semantics, and `quick_flip`/`held_seconds` semantics on SELL rows. This is exactly the beyond-annotation context the dimension rewards.

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?

Purpose and the sibling differentiation are front-loaded, and the long context-field sentence is genuinely informative rather than filler. The output is dense and near the edge of what one paragraph should carry; a few clauses could be split or trimmed, keeping it just below a 5.

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 12-parameter, cursor-paginated feed tool, the description covers the window constraint, pagination loop, ordering, filtering dimensions, row-level fields, and null behavior. With an output schema present, it appropriately does not restate the return envelope, and nothing needed to call it correctly 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 92%, so the baseline is 3; the description adds real value by explaining `include_context`'s per-row block field-by-field (pnl_pct_vs_entry, tags, hold_days_at_trade, share_sold_of_position, days_since_prev_trade, wallet_win_rate) and the 'wallets waking up after a quiet spell' interpretation of `min_days_since_prev_trade`. It doesn't restate all filter parameters, but it compensates well where the schema is thin.

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 specific verb+resource+scope ('every tracked-whale buy and sell inside one time window, at most 48 hours') and explicitly contrasts with sibling `get_whalewatch_feed` (one row per swap vs. repeated per list). An agent can distinguish it from the other whalewatch feed tools without opening a 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?

Explicitly says when to use it ('bulk reads such as everything whales did in the last 6 hours'), when not to (the plain feed for non-deduplicated reads), and routes to `get_whale_wallet_track_record(wallet_address)` for wallet quality. It also pre-empts a likely misuse by clarifying this is public market data, not `get_my_*` user data.

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