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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, open-world), and the description adds genuinely new operational context: a free tier metered by a daily per-caller quota, and the exact payment mechanism (X-Payment / X-Payment-Tx / Bearer token in request headers, explicitly not in parameters). That auth/payment detail is the kind of thing an agent would otherwise get wrong. It stops short of noting rate-limit behavior beyond the quota or whether results are cached.

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 useful content is front-loaded in the first two sentences, but the block is then restated in Chinese, then again in a [zh]/[en] pair, so the same payload is delivered roughly three times. The payment-header note is valuable, yet the duplication inflates length without adding information and pushes the parameter notes away from where they matter.

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 compensate by enumerating return fields (route, gross/net spread, pool depth, CEX prices, verdict, confidence), and payment/auth is covered. What is missing for a 4-param, zero-coverage schema is parameter meaning and any indication of how results are ranked or what happens when no spread exists. Adequate but with a clear gap on the input side.

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 description coverage is 0%, so the description carries the full burden, but it only restates which parameter is required (symbol) and lists the three optional ones by name — information already encoded in the schema's required array. There is no explanation of what quote means (quote currency vs. chain), what token identifies (address vs. symbol), or what unit/threshold min_liquidity expects. The semantics gap is left entirely open.

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?

The opening sentence frames a concrete question ("is there an arbitrage spread right now?") and then enumerates the specific payload: best route, buy/sell venue, gross spread, net-of-fee spread, DEX pool liquidity, four CEX prices, viability verdict, confidence. That is a specific verb+resource statement an agent can match against a user request. It does not name any sibling (e.g. arb-spread.route_detail) to sharpen the boundary, which keeps it from a 5.

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 "is there an arbitrage spread right now" framing implies the triggering scenario, and the daily free quota is stated, so the agent knows the cost model. However there is no explicit when-not-to-use and no mention of when to prefer arb-spread.route_detail for drill-down or funding-spread.scan for the alternative strategy. Guidance is implied rather than stated.

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