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

With no annotations, the description carries full behavioral burden. It does disclose key operational traits: payment requirements (API key or per-call fees via specific payment rails), the default and max values for active_hours and limit, and the set of supported chains. However, it does not state whether the operation is read-only, what happens on empty results, or any rate limits or error handling. The disclosure of defaults and chains is useful but incomplete for a tool with no annotations.

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 description is not front-loaded with the primary purpose; it begins with payment details, which obscures the tool's function. The information is packed into a few sentences but could be reorganized to state the purpose first, then constraints and defaults. It's not overly verbose but structure is suboptimal, and the payment sentence is long and detailed, possibly distracting.

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?

Given the existence of an output schema, the description does not need to detail return structures, and it does list key output fields. It covers supported chains, defaults, and payment methods. However, it lacks explicit guidance on parameter semantics and usage context, and does not mention pagination or error conditions. For a tool with 3 parameters, one required, and no annotations, the description is not fully complete; an agent might still be uncertain about how to set active_hours or what limit controls.

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. It provides default values (active_hours=168, limit=50, max=200) and lists the chains for the chain parameter, but does not explain the meaning or units of limit and active_hours beyond implying time and count. The ordering 'by detections' hints at limit's role but not explicitly. Without clear param semantics, an agent may misuse the parameters, especially active_hours (is it hours? blocks?).

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 states the resource: 'Active MEV bot addresses on a chain' and lists the fields returned (detections, strategy types seen, first/last seen, high confidence flag). It also specifies ordering by detections, which differentiates it from sibling tools like mev_pressure or mev_intel that likely focus on aggregate metrics. Though the first sentence is about payment, the core purpose is unambiguous and specific.

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 implies usage (call this tool to get active MEV bots on a chain) but does not explicitly state when to use it versus alternatives, nor exclude any contexts. No mention of when not to use it, prerequisites beyond payment, or relationships to sibling tools like mev_flow_spec or mev_pressure. The payment requirements are stated but not framed as usage guidance.

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