MEV Intelligence

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds valuable context beyond annotations: it explicitly states 'does NOT touch funds and does NOT submit anything' and clarifies it is 'a calldata builder'. No contradiction with annotations; the added safety framing earns a 4.

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?

Three sentences, front-loaded with the core purpose, followed by return contents and safety disclaimers. Every sentence earns its place; no fluff or redundancy.

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 complexity (10 params, 3 protocols, 2 chains) and the rich schema/annotations, the description covers the essential context: supported protocol/chain combos, what the tool returns, and its non-submitting nature. It doesn't enumerate edge cases like Morpho-specific parameter behavior, but the schema already handles that, and the description sufficiently frames the tool's role.

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 coverage is 100% — every parameter has a description in the schema. The tool description adds no parameter-level semantics beyond the schema; it only summarizes supported protocols and return fields. Per the rubric, baseline 3 is appropriate when the schema does the heavy lifting.

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 opens with a specific verb+resource: 'Build agent-ready calldata for a liquidation transaction.' It further clarifies what is returned (target contract address, calldata, gas limit, value, chain) and explicitly differentiates from sibling tools like submit_bundle and the various get_* tools by stating it builds calldata only and does not submit.

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 clearly establishes when to use the tool: to produce calldata that an agent will later sign and submit via submit_bundle. It also implies a contrast with submit_bundle by stating this tool does not submit anything, but it does not explicitly name alternative tools or exclusion criteria, so it falls short of a 5.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds behavioral context: it operates on live relay acceptance rate and submission volume, returns only the top builder and acceptance percentage, and notes that a full ranked list requires x402 payment.

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 only two sentences, front-loading the core purpose and then adding the output details and the paid alternative. No wasted words.

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?

With no parameters, no output schema, and simple scalar return values, the description fully covers what the tool does and what the user will get. It even points to an extended endpoint for more data, making it contextually complete.

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?

There are zero parameters, so there is nothing to explain beyond the schema. The description focuses on the tool's behavior and output, which is appropriate for an empty input 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 states the tool's function: 'Get the best Ethereum block builder for MEV bundle submission RIGHT NOW based on live relay acceptance rate and submission volume.' It specifically names the resource (builder recommendation) and the output (builder name and acceptance percentage), distinguishing it from siblings like recommend_bundle_submission.

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 context for real-time use ('RIGHT NOW') and mentions the full ranked list is available at another endpoint with payment, implicitly guiding users who need more than the top recommendation. It could explicitly name when not to use or cite alternatives, but the context is strong enough.

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

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

Annotations already declare the tool as read-only, non-destructive, and open-world. The description adds useful context beyond annotations, such as the report's content (funnel metrics, top candidate) and the availability of a full accuracy archive at a specific path. This enriches the agent's understanding of what the tool returns and where to find deeper data, although it does not address performance or rate limits.

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 concise and front-loaded, consisting of two sentences that each serve a purpose: the first defines what the tool does and lists key metrics, the second points to the accuracy archive. No filler or redundancy.

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 single parameter, rich annotations, and absence of an output schema, the description is complete enough for the agent to understand what the tool returns (summary of market activity) and when to call it. It covers the essential context without needing to explain return values or parameter details.

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 fully documents the only parameter (window_hours) with description 'Lookback window in hours (default 24, max 48).' The tool description adds no additional semantic meaning about the parameter beyond the schema, so it meets the baseline for high schema coverage without further value.

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 purpose: 'Get a daily intelligence report summarizing liquidation market activity' with a specific list of contents (competitor count, positions, funnel metrics, top candidate). It distinguishes itself from sibling tools by framing itself as the 'morning briefing' tool, setting it apart from more granular tools like get_liquidation_waves or get_mev_feed.

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 explicit usage guidance: 'call it once per session to understand market state before executing.' This clearly indicates when to use the tool, but it does not explicitly mention alternatives or when-not-to-use scenarios, so it stops short of a perfect score.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is known. The description adds valuable context beyond annotations: it returns only the top 10 positions (preview), the limit parameter has a max of 10, and it lists the exact return fields, which is useful for the agent to understand the tool's scope and limitations.

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 concise: three sentences cover purpose, output, and workflow. No redundancy or filler—each sentence earns its place. The main purpose is front-loaded, making it easy for an agent to quickly understand the tool.

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 tool's simplicity (one optional parameter, read-only, no nested objects) and the absence of an output schema, the description is complete. It lists return fields, states the preview limitation, and provides workflow context (submit_bundle) and an alternative for extended needs. This is sufficient for an agent to select and invoke the tool correctly.

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 100% coverage for the single 'limit' parameter, including its default and max values. The description does not add new parameter-specific information beyond what the schema offers, but since the parameter is simple and self-explanatory, a baseline score of 3 is appropriate.

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 gets near-liquidation borrowers ranked by health factor proximity across Aave V3, Spark, and Morpho on L1 and Base. It specifies the exact output fields (borrower addresses, health factor, debt USD, collateral USD) and differentiates from siblings like get_mev_feed or predict_liquidation_probability by focusing on ranked borrower lists.

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 explicitly tells the agent to use this tool to get targets, then sign a liquidation transaction and call submit_bundle for atomic execution. It also directs to the paid endpoint /intelligence/liquidation-waves for net profit estimates and the full borrower universe, establishing when not to use this tool.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, so the read-only nature is covered. The description adds behavioral detail by stating it returns exactly 10 positions, lists the included fields, and discloses that the full stream requires payment—useful context beyond the 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 concise and front-loaded, consisting of four short sentences each adding distinct value: the purpose, return contents, a paid alternative, and the action sibling. No wasted words.

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?

Without an output schema, the description adequately covers the return value by listing the fields (chain, protocol, health factor, risk tags) and the count (10). It also mentions the existence of a paid full stream for additional data, which is valuable context. Minor gaps include lack of ordering or default behavior, but it's sufficient for a simple read-only feed.

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 100% for the single parameter min_net_usd, which is clearly described as 'Minimum estimated net USD profit to include'. The tool description does not add additional meaning to this parameter, so the baseline score of 3 is appropriate.

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 'Get a risk-enriched MEV opportunity stream' and specifies the return contents (10 positions with chain, protocol, health factor, risk tags). It distinguishes itself from siblings by mentioning acting via submit_bundle and a paid full stream, implying this is the limited free feed.

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 context for use: it returns a limited 10-position feed, while the full stream with borrower addresses and expected profit is available at /intelligence/feed at a cost. It also directs users to submit_bundle to act on opportunities, giving an alternative for follow-up actions. However, it does not explicitly contrast with other sibling read tools like get_daily_liquidation_report.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds behavioral details beyond that: it specifies the 4-hour time window, the return fields (full addresses, landed count, total submissions, land rate percentage), and that only the top 5 are free, with a paid full version. This provides useful context about what the operation does and its limitations.

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 two sentences, with the primary action and scope in the first sentence, followed by specific return details and an alternative in the second. Every sentence adds value, with no redundancy or fluff.

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 tool has no parameters and no output schema, the description covers the essentials: what the tool returns, the ranking criteria, the time window, and how to access the full leaderboard. This is a complete and self-contained description for this simple tool.

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 has zero parameters, so the schema coverage is 100% by default. The description doesn't need to explain parameter semantics; the baseline of 4 applies as no parameters exist that require additional explanation.

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 retrieves top MEV searchers ranked by landed liquidation fires in the last 4 hours, with a specific verb and resource. It differentiates from sibling tools like get_liquidation_waves or get_daily_liquidation_report by focusing on the leaderboard metric.

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 indicates this returns the top 5 free, and mentions the full 25-entry leaderboard requires x402 payment, giving context for when to use the free subset vs an alternative. However, it doesn't explicitly name sibling tools or state when not to use this tool, so guidelines are only partially explicit.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is clear. The description adds valuable behavioral context beyond annotations, such as the ordering by cross probability, the nature of the data (predicted next price move), and the intended workflow (pre-building bundles). This goes beyond the structured annotations without contradicting them.

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 two sentences, with the main purpose front-loaded, followed by output details and actionable usage guidance. Every sentence adds value without redundancy. It is tightly written and avoids filler.

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?

Despite lacking an output schema, the description enumerates the returned fields (health factor, cross probability, net profit, protocol) and explains the sort order and intended use. Parameters are fully described in the schema. The tool's role in the overall workflow is clear, and it connects to a sibling action (submit_bundle). This is complete for the tool's complexity.

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 coverage is 100%, so baseline is 3. The description adds minimal meaning beyond the schema: it implies that min_cross_prob filters 'high-priority' candidates, but the schema already explains the parameters fully. The description does not introduce new parameter semantics, so it meets but does not exceed the baseline.

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 a specific verb+resource: 'Get the highest-priority liquidation candidates sorted by cross probability.' It specifies the exact output fields (health factor, cross probability, net profit, protocol) and distinguishes itself from siblings by focusing on cross-probability-based prioritization for pre-building bundles.

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 explicitly tells when to use the tool: 'Use this to prioritize which positions to pre-build bundles for.' It also provides a clear trigger for a sibling tool: 'Call submit_bundle when a candidate crosses HF=1.0.' While it doesn't explicitly name alternatives, the unique focus on cross probability implies differentiation from report-style siblings like get_daily_liquidation_report.

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

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

Annotations already indicate read-only and non-destructive behavior. The description adds meaningful detail about the returned fields, including units (e.g., oracle_velocity as |Δprice|/min) and the nature of the prediction (health_factor, cross_probability). It also notes the distinction between this tool and the full paid model. No contradictions found.

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 somewhat long but well-structured, with a clear list of return fields and a strategic usage note. It front-loads the primary function and then provides actionable guidance. Every sentence contributes value, though the length could be slightly trimmed without losing meaning.

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 there is no output schema, the description adequately enumerates the return values and their meanings. It also situates the tool within the workflow (before submit_bundle) and mentions a premium alternative. It could be more explicit about data freshness or potential inconsistencies, but overall it covers the essential context for an agent to decide when to use the tool.

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 coverage is 100% for the two parameters, so the baseline is 3. The description adds extra semantics: 'If omitted, returns top 5 candidates by cross probability' and 'Optional protocol filter when borrower is not specified.' This clarifies conditional behavior beyond the schema's simple field descriptions.

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 tool's purpose: 'Get a structured liquidation probability prediction for a specific borrower or the top candidates.' It specifies the resource (borrower/candidates) and distinguishes it from siblings by calling it 'the core moat tool' that drives bundle decisions. The verb 'Get' is direct and the scope is unambiguous.

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 gives explicit usage context: 'Call this before submit_bundle to confirm the opportunity is still live and to size your bribe correctly.' It also explains behavior when borrower is omitted and mentions an alternative (the paid /intelligence/liquidation-waves endpoint). It doesn't explicitly list exclusions, but the guidance is clear and actionable.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description doesn't repeat safety traits. It adds valuable context by explaining the recommendation is based on live relay telemetry and includes expected inclusion probability, which goes beyond the annotations in describing what the tool actually returns.

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, front-loaded with the core purpose, then the return payload, then a specific usage pairing. Every sentence contributes meaning with no redundancy or filler.

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 read-only, single-optional-parameter tool with no output schema, the description fully covers the purpose, return value, and recommended workflow. It equips the agent to understand when and how to invoke the tool without requiring further clarification.

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 describes the 'borrower' parameter with 100% coverage. The description adds the key semantic detail that omitting the borrower yields a recommendation for current market conditions, which the schema does not state. This clarifies the optional parameter's behavior more fully.

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 specifies the verb 'Get' and resource 'actionable bundle submission recommendation', and details the exact return values (builder, inclusion probability, reason). It distinguishes itself from siblings by framing it for deciding WHERE to submit a bundle, especially referencing pairing with monitor_crossing_candidates.

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?

Explicitly instructs to pair with monitor_crossing_candidates: 'identify a hot candidate, then call this to decide WHERE to submit your bundle'. Also clarifies the two invocation modes (specific borrower vs. current market conditions), giving clear when-to-use guidance.

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

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

The description goes well beyond the basic annotations by disclosing operational details: bundles are fanned out to multiple relays (Flashbots, Titan, Beaver, BuilderNet, bloXroute), it's 'Free with API key attribution,' analytics are available at a specific endpoint, and submission status can be tracked via tracking_id. This gives the agent a full picture of side effects and follow-up actions.

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 fairly lengthy but well-structured: it starts with the core purpose, then usage timing, then behavior (relay fanout, analytics), then return value, and finishes with a practical tip. Every sentence adds valuable context, though it could be slightly more concise without losing 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?

Given the tool's complexity (submitting bundles to multiple relays, requiring signed txs, tracking status), the description covers all essential aspects: what it does, when to use it, side effects, return value (tracking_id), and supplementary endpoints. With no output schema, the inclusion of tracking_id is especially helpful. It feels complete for the task.

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 coverage is 100%, so baseline is 3. The description adds contextual meaning by emphasizing that txs must be signed, mentioning the max of 10 per bundle, and explaining the api_key is for attribution (and that the tool is free with it). This reinforces and slightly extends the schema descriptions, earning a 4.

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 purpose: 'Submit a signed Ethereum bundle directly to MEV SearcherNet rbuilder for inclusion.' This uses a specific verb (submit) and resource (signed Ethereum bundle) and distinguishes it from sibling analytics/viewer tools by being the action tool.

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?

Explicit usage context: 'Use this after get_liquidation_waves or get_mev_feed to act on a liquidation opportunity.' It also provides a workflow pair with get_liquidation_waves, showing exactly when this tool fits relative to others. While it doesn't explicitly say 'when not to use,' the after X language makes the appropriate context clear.

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