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

With no annotations, the description carries the disclosure burden, and it does add meaningful context: it discloses that detection rules are versioned/datable ("in force and their dates") and that outputs can be re-derived via public RPC. It does not describe response size, format, or whether the spec is versioned as a whole, so it is adequate but not rich.

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 states purpose first and then itemizes contents, with no filler or restatement of the name. The trailing list is dense but each clause covers a distinct content area, so it earns its length.

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?

The tool is a zero-parameter, read-only spec document and an output schema exists, so return-format details need not be in the description. The description covers what the document contains and its verification angle; only the explicit sibling-routing guidance is missing.

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 no parameter semantics to explain; the schema confirms an empty, closed object (additionalProperties: false). Baseline 4 applies since the description has nothing to compensate for and correctly introduces no argument concepts.

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 description clearly frames this as a reference/spec resource: how MEV order-flow data is produced and how to independently verify it, with an enumerated inventory of contents (chains, event types, detection rules, stream event, row fields, RPC re-derivation). That is a specific resource distinct from data-returning siblings like mev_intel, mev_pressure, and victim_flow. It does not, however, explicitly contrast itself with those siblings, so it stays at 4 rather than 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?

"How to check it yourself" and the pointer to registering for the stream event imply this is read before consuming or verifying MEV flow data, which is a usable implied usage context. But no explicit when-to-use / when-not-to-use guidance or named alternatives (mev_intel vs mev_pool_check vs victim_flow) are given, leaving the agent to infer routing.

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