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

Annotations already declare readOnly/openWorld/non-destructive, and the description goes meaningfully beyond them: stats-only payload (no holdings), the partial-result rule ('a wallet Moby has never seen is left out — match rows on wallet_ref'), and the input provenance requirement. It does not explain why `idempotentHint` is false (data drifting between calls), which is the one annotation-relevant trait left unaddressed.

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 the action, batch size, and payload shape; field names and sibling routing follow logically. The tail loses a point for redundancy — 'never the user's wallet', 'NOT about the user's own wallet', and the `get_my_` pointer restate the same disambiguation three times.

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?

Despite an output schema existing, the description still names the returned fields (`windows.d7`/`d30`, `track_record`, `realized`, `identity`), which is more than required. Caller has everything needed: where the refs come from, the cap, what comes back, and how to handle missing wallets.

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 50%, and the description compensates on the important half: `wallet_addresses` are 'refs from get_token_key_holders', capped at 20, plus the warning to match returned rows on `wallet_ref` rather than assuming positional correspondence. `network` is undocumented but is a fixed const 'solana', so the gap is low-risk.

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?

Specific verb + resource ('Rate 10-20 key holders' / whale wallet profiles) with explicit batch scope. It immediately separates itself from the singular sibling by naming `get_whale_wallet_profile` as the one-wallet alternative and by stating 'stats only, no holdings' versus the holdings tool.

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?

Gives a concrete use case ('before a buy'), a concrete input source (`get_token_key_holders` refs, max 20), and an explicit alternative for the single-wallet case. The exclusion 'never the user's wallet' plus the routing rule for `get_my_*` tools closes the most likely mis-selection path in this catalog.

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