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

Annotations already cover the safety profile (readOnly, idempotent, closed-world), so the description's real contribution is behavioral: it discloses that returns are computed NET after fees and slippage at the caller's size, and that the 7-day sum is settled rather than projected. That materially changes how an agent interprets the numbers. It stops short of describing pagination, errors, or how many exchanges/pairs come back.

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?

A single front-loaded sentence that leads with the resource ('Funding rate of one coin on every exchange') before the returned-fields parenthetical. Dense but every clause carries information; the parenthetical field list is the only slightly heavy section, though it substitutes for a missing output schema.

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 carries the return-value burden and does so by enumerating the fields (rate, interval, APR, predicted, OI, volume, settled 7-day sum) plus 'best pairs' net of costs. For a 2-parameter read tool whose annotations are already rich, that is nearly sufficient; what's missing is how 'best pairs' is ranked and roughly what volume of results to expect.

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 100%, so the baseline would be 3; the description earns an extra point by explaining what `notional` actually does — it drives the fee/slippage deduction, so changing it changes the reported net figures, not just a filter. It also ties `base` to the 'one coin' scope. Minor gaps: no restatement of the default (10000) or the 10–100M bounds, though the schema carries those.

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: funding rate of ONE coin across EVERY exchange, plus best pairs — this is the mirror image of a per-exchange scan and an agent can infer the distinction. However, it never names the sibling it contrasts with (funding_rates, exchange_overview), so the differentiation is inferential rather than explicit.

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?

Usage is only implied by the content list — the agent must infer you call this when you want one asset's cross-venue funding picture rather than a market-wide scan. There is no statement of when not to use it, no prerequisites, and no named alternative among the 26 siblings.

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