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

With annotations only covering read-only and open-world hints, the description adds substantial behavioral context: per-call cost and payment paths, on-chain source, 3-minute refresh cadence, and a documented degradation path where a failed chain returns stale_last_good with as_of/block/age_seconds plus spread_ok/max_spread_seconds per figure. That is exactly the failure-mode and freshness detail an agent cannot infer from structured fields.

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 price and the tool's identity are front-loaded, and the dense enumeration of tracked fields is efficient for a no-output-schema tool. It is telegraphic and abbreviation-heavy (moved 1h/24h, stale_last_good) but almost no sentence 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?

With no output schema, the description does the work of listing returned fields (holdings, frozen status, transfers, swaps, bridge/mixer, inflow alerts, 1h/24h movement) and covers chains, staleness and cost. The remaining gap is the unexplained limit parameter and default result size.

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 67%: api_key is fully documented in the schema and incident carries its value (binance-2026), but the description never explains what limit controls or what the default page size is. The description adds rich content about returned figures but no parameter-level meaning beyond 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?

Names a specific resource and scope: a stolen-funds tracker for the Binance Oct 2026 hack, enumerating attacker and linked wallets with holdings, frozen status, outbound transfers, swaps, bridge/mixer use and exchange-inflow alerts. That is far more specific than any sibling (binance_flows, address_poisoning, wallet_profile), though it never explicitly contrasts itself with them.

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?

The scope (hack/exploit attribution and attacker wallet tracing) strongly implies when to call it, and the leading 'PAID $0.03 USDC' signals a cost tradeoff against free siblings such as free_binance_flows. But there is no explicit when-to-use/when-not statement and no named alternative for cheaper or broader flow queries.

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