Get a risk-enriched MEV opportunity stream. Returns 10 positions with chain, protocol, health factor, and risk tags. Full stream with borrower addresses and expected profit available at /intelligence/feed with x402 payment ($0.10). Use submit_bundle to act on opportunities directly from this feed.
| Name | Required | Description | Default |
|---|---|---|---|
| min_net_usd | No | Minimum estimated net USD profit to include |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the tool's safety profile is known. The description adds valuable behavioral context: it returns exactly 10 positions, lists the fields included, and discloses that a fuller stream is available via paid endpoint. This goes beyond the annotations by setting expectations about response size and data limitations. No contradiction with 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 three sentences with no redundant words. It front-loads the primary action, then gives return details, and finally provides alternative/premium options. Every sentence contributes useful information.
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?
For a simple read-only tool with one optional parameter and no output schema, the description is sufficiently complete. It specifies the return size, key fields, and the related action tool (submit_bundle), while annotations cover safety. It also informs about the paid full stream, which is relevant context for agents with payment capabilities.
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 schema already provides a complete description for the only parameter (min_net_usd: 'Minimum estimated net USD profit to include'), giving 100% coverage. The tool description adds no additional meaning about this parameter, so the baseline score of 3 applies because the schema handles the semantic burden.
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 tool's function with a specific verb and resource: 'Get a risk-enriched MEV opportunity stream.' It also lists the exact return fields (chain, protocol, health factor, risk tags) and explicitly mentions the sibling tool submit_bundle for acting on opportunities, distinguishing it from that action-oriented sibling.
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 provides clear usage context by stating 'Use submit_bundle to act on opportunities directly from this feed,' which directs the agent to the appropriate alternative for a follow-up action. It also mentions that the full stream requires x402 payment at another endpoint, implying this feed is a limited/preview option. However, it does not contrast this tool with other read-only siblings like get_daily_liquidation_report or get_liquidation_waves, so some exclusion guidance is missing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct purpose: building calldata, getting builder recommendations, daily reports, listing borrowers, grabbing an opportunity stream, viewing leaderboards, monitoring crossing candidates, predicting probabilities, recommending submission, and submitting bundles. No overlapping functionality.
All tool names follow a consistent verb_noun pattern in lower_snake_case (e.g., build_liquidation_tx, get_builder_recommendation, submit_bundle), making it easy to predict tool behavior from names.
With 10 tools, the set is well-scoped for an MEV intelligence server. It covers the full workflow from opportunity discovery to bundle submission without being bloated or sparse.
The tool set covers the core liquidation workflow comprehensively (identify, predict, build, recommend, submit). A minor gap is the lack of a dedicated tool to check submission status, relying on an external endpoint instead.