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

With no annotations provided, the description carries the full burden and delivers substantive disclosure: authentication/payment requirements (bearer token or pay-per-call rails), the semantic claim that a backrun row also emits an arbitrage row, and the ERC-721-only NFT coverage limit. These go well beyond what the bare schema reveals, though it stops short of describing rate limits or omitted-parameter behavior.

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?

Every sentence earns its place — payment, purpose, window bounds, overlap warning, coverage note — with zero filler or repetition. The structure is a single dense paragraph, and the verbose payment options dominate the opening, burying the actual purpose statement in the middle rather than front-loading it.

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?

Since an output schema exists, return-value documentation is handled elsewhere, and the description covers the remaining essentials: how to authenticate/pay, window semantics, and two critical data-interpretation caveats (type overlap, ERC-721 scope). The main omissions are what an omitted chain parameter returns and a full enumeration of the MEV types referenced by example.

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 must compensate, and it meaningfully does for window by specifying units (hours), default (24), and maximum (168). The chain parameter is left to its self-documenting enum of nine chain names, and since both parameters are optional, the description never explains what omitting chain or window yields — a real gap at 0% coverage.

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 core phrase 'MEV event rates per chain and type vs the trailing weekly pace' identifies a specific resource, granularity, and comparison baseline, which is clear enough to distinguish it from most siblings. However, it lacks an explicit verb (get/query/report), arrives only after the payment sentence, and never names the near-sibling mev_bots to preempt confusion.

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 description supplies usable invocation guidance: 'window in hours, default 24, max 168' sets parameter bounds, 'Types overlap and must not be summed' tells the agent how to interpret rows, and the ERC-721 note flags a coverage exclusion. It never states when to choose this tool over alternatives like mev_bots, so selection context is implied rather than explicit.

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