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

Goes well beyond the readOnlyHint/openWorldHint annotations: it documents per-chain check states (checked_ok, checked_ok_empty = real zero, not_checked = null total, error), freshness fields (last_success_at/last_error_at, as-of time and block), and staleness controls (spread_ok/max_spread_seconds with the limit defined as measured loop cycle + grace). The noteworthy caveat that BSC is 1h only is disclosed. This is exactly the data-quality context annotations cannot carry.

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 FREE marker and the core measurement, then layers the per-chain state semantics and the paid alternatives. Every clause carries information, but the single dense paragraph with semicolon-chained clauses is harder to scan than a short structured list would be.

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?

There is no output schema, so the description must carry the return shape, and it does: totals across chains plus per-chain breakdown, check states, freshness timestamps, and spread metrics. Combined with the alternative-tool routing and the BSC coverage caveat, an agent has everything needed to call and interpret it.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline is 4. The description correctly implies a no-argument call rather than inventing filters, though there is no explicit statement that the call takes no inputs.

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 measurement (net USD outflow from Binance's publicly identified wallets) with exact time windows (1h and 24h), scope (all chains and per chain, naming Ethereum, BSC, Base, Tron, Bitcoin), and pricing basis (Chainlink). This is clearly distinguishable from the sibling binance_flows and binance_flows_report tools, which are explicitly called out as deeper/paid variants.

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 frames this as the FREE headline and names both alternatives with their incremental value and cost: 'binance_flows ($0.02) adds per-asset detail; binance_flows_report ($0.25) adds biggest withdrawals and destinations.' An agent can pick among the three on cost/depth with no inference.

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