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

With no annotations to lean on, the description discloses key behavioral information: authentication requirements (ChainHelix API key or paid payment), the data included, the sort order, and the limit boundary of 200. It does not cover every detail like rate limiting or pagination, but For a listing tool it does a solid job of setting expectations.

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 text is substantively informative but front-loads payment/authentication details in a dense first sentence, which delays stating the tool's purpose. The second sentence is concise and information-rich, but the ordering is suboptimal for agents scanning to understand what the tool does.

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 output schema is present and need not explain return values, the description covers the conventional main points: what the tool returns, order preferences, default filters, maximum values, and auth/payment requirements. The largest gap is not referencing the related sibling mev_intel or clarifying ambiguous field names like active_hours.

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 semantically elevated to compensate. It does provide default for active_hours (168), default limit (50), and max limit (200), but it never explicitly explains that active_hours defines the lookback window for 'active' bots or that limit is the number of results returned. The chain parameter is left is well covered by the enum in the schema.

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 identifies the output as active MEV bot addresses on a chain, including detections count, strategy types seen, first/last seen timestamps, and a high-confidence flag. The scope is clear, but it lacks an explicit verb like 'List' or 'Return' and does not distinguish itself from the sibling tool mev_intel.

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 mentions operational constraints such as the API key requirement, default values for active_hours and limit, and a maximum limit of 200. However, it never explicitly states when to use this tool versus alternatives like mev_intel, and there is no exclusion guidance; the use case is only implied.

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