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

Annotations cover the safety profile (readOnly, non-destructive), and the description adds context they cannot: `data_as_of` freshness semantics, that unseen-but-known wallets return null sections rather than an error, that `include_holdings=false` nulls both holdings and the read section, and that `identity.tracking_paused_at` signals Moby stopped tracking. It also tells the agent how to interpret results (no colour; use `read.situation` + window stats), which is genuinely non-obvious behavior.

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?

The opening is front-loaded and dense with useful signal, but the closing three sentences all restate the same warning ('never the user's profile… NOT about the user's own wallet… `get_my_` tools return the user's own data'). That is roughly a third of the text spent on one point already made once, which dilutes the higher-value content above it.

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 names the key result fields (`windows.d7`/`d30` P/L, closes, win rate, hold days, sub-24h share) so the agent knows what it can answer with this call. Combined with freshness, null-return, and scale-out guidance, nothing needed to invoke or interpret 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?

At 67% schema coverage, the description adds real meaning for `include_holdings` — not just 'smaller, faster' as the schema says, but that holdings AND the read section come back null. `wallet_address` opaque-reference behavior is already in the schema, and `network` is a const so needs no explanation. Good compensation, though not exhaustive.

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 ('one call combining identity, realized track record, current holdings, recent trades') and names the exact sibling calls it replaces (`get_whale_wallet_track_record` + `get_whale_wallet_positions`). An agent can distinguish it from `get_whale_wallet_holdings`, `get_whale_wallet_profiles`, and the `get_my_*` family 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?

Explicit routing rules: prefer this over the two separate calls, use `get_whale_wallet_profiles` when rating many wallets, use `include_holdings=false` for the cheap path, and use `get_my_*` tools for the user's own wallet. The when-not-to-use case (user's own data) is stated twice, which is over-insured but unambiguous.

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