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

With no annotations, the description carries the full burden. It usefully discloses that rates are annualized to normalize differing funding intervals and that a cheapest-vs-richest spread is computed, which is genuine behavioral context. But it leaves 'predicted' undefined (source, freshness, update cadence) and says nothing about return shape, auth, or rate limits.

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-loads the resource and scope in one dense sentence, then adds an interpretive sentence that earns its place by explaining how to act on the signal. The redundant tool-name prefix at the start is the only waste.

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?

No annotations, no output schema, and four undocumented parameters with an unresolved coin/symbol ambiguity plus an oddly string-typed limit and minSpreadPct threshold. For a tool of this complexity the description omits the parameter and output detail an agent needs to invoke it correctly.

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 0% for four parameters, so the description must compensate and largely does not. It only gestures at 'coin'; it never clarifies the coin-vs-symbol overlap (two seemingly redundant identifiers) or what 'limit' (typed as a string) or 'minSpreadPct' do. An agent has no basis to disambiguate the identifiers.

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?

State a specific resource (predicted funding rates across venues, annualized, with a cross-venue spread) and clearly differentiates itself from the single-venue funding siblings by scope. It stops short of naming the sibling (e.g. x402-hyperliquid-funding) it should be chosen over, so the distinction is inferred rather than stated.

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 second sentence gives a real usage context ('cross-exchange funding arbitrage signal: long where funding is lowest, short where it is highest'), which tells an agent what the output is for. However it offers no when-not guidance, no prerequisites, and no explicit alternative tool to use instead for single-venue or realized-funding queries.

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