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 and destructiveHint, and the description adds context by explaining the data sources (live relay acceptance rate and submission volume) and that it returns only the top recommendation. It also mentions a paid endpoint for full telemetry, which is useful behavioral context beyond 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?

Two sentences, front-loaded with the core purpose and outcome. The second sentence efficiently introduces the extended resource and payment requirement without unnecessary detail.

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 no output schema, the description is complete: it explains the recommendation criteria, the returned data (builder name and acceptance percentage), and a pointer to the full ranked list. No key information is missing for an AI agent to use this tool effectively.

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?

With zero parameters, the description fully compensates by explaining what the tool does and what it returns. There is no need for parameter-level semantics, and the description provides enough detail about outputs and criteria.

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 action: getting the best Ethereum block builder for MEV bundle submission right now, based on live relay acceptance rate and submission volume. It distinguishes from siblings like recommend_bundle_submission by focusing on builder selection, and specifies the return value (builder name and acceptance percentage).

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?

Provides clear context: use this when you need the best builder immediately based on live telemetry. It also points to an alternative endpoint for the full ranked list with payment, but does not explicitly exclude or contrast with sibling tools such as recommend_bundle_submission.

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 read-only, non-destructive, and open-world behavior. The description adds value beyond annotations by specifying the 'morning briefing' usage pattern, the report's scope, and pointing to a full accuracy archive at /intelligence/accuracy-archive for deeper metrics. This provides behavioral context without contradicting 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, each earning its place: the first states the purpose and contents, the second gives usage guidance, and the third points to supplementary resources. It is front-loaded, efficient, and free of 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?

For a simple read-only report with one optional parameter and no output schema, the description is complete. It explains what the report contains, when to call it, and where to find more detailed accuracy metrics, fully equipping the 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?

Schema coverage is 100%, with the single parameter 'window_hours' already described in the schema ('Lookback window in hours (default 24, max 48)'). The tool description does not add any parameter-specific meaning beyond the schema, 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's purpose with a specific verb ('Get') and resource ('daily intelligence report summarizing liquidation market activity'). It enumerates the report's contents (competitor count, positions, funnel metrics, top candidate) and distinguishes it from sibling tools by positioning it as the 'morning briefing' 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?

The description provides explicit when-to-use guidance: 'call it once per session to understand market state before executing.' This contextualizes the tool within a workflow and implies it should be used before other execution tools, offering clear usage direction without needing to name alternatives.

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 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.

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 read-only nature is covered. The description adds transparency about the output fields (health factor, cross probability, net profit, protocol) and sorting by cross probability, which is useful for understanding behavior without an output schema. It does not disclose pagination or rate limits, but this is minor given the tool's simplicity.

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 four concise sentences, each adding meaningful information: purpose, output contents, usage, and follow-up action. It is front-loaded with a clear verb+resource and contains no redundant or filler text.

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 query tool with two simple, documented parameters and no output schema, this description is comprehensive. It covers what the tool does, what it returns, when to use it, and what to do next, making it effectively complete 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 input schema covers 100% of parameters with descriptions for both limit and min_cross_prob, so the schema does the heavy lifting. The description adds no additional parameter details, though it does mention cross probability (0–1) in the context of the returned data. Baseline 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 it 'Get[s] the highest-priority liquidation candidates sorted by cross probability', identifies the target resource, and explains what each candidate includes. It differentiates from sibling tools by focusing on prioritization for pre-building bundles, which is distinct from prediction, reporting, or submission tools.

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?

It explicitly says to use this tool to 'prioritize which positions to pre-build bundles for' and instructs to 'Call submit_bundle when a candidate crosses HF=1.0', giving clear usage context and a follow-up action. However, it does not mention when to use alternative tools like predict_liquidation_probability or get_liquidation_waves, so it lacks explicit exclusions.

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 mark this as read-only and non-destructive. The description adds valuable behavior beyond annotations: it uses live relay telemetry, falls back to market conditions when no borrower is specified, and returns a human-readable reason. No contradiction exists.

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, each with clear purpose: the action, the return values, and the workflow pairing. No filler or redundancy. Front-loaded and well structured.

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 tool with one optional parameter, no output schema, and a read-only annotation, the description is complete. It explains what it does, what it returns, and when to use it. The return shape is described enough in prose to compensate for the missing output schema.

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 documents the single optional 'borrower' parameter at 100% coverage. The description adds important semantic nuance: omitting the borrower switches to market-conditions mode. This extra meaning goes beyond the schema description, justifying 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: getting an actionable bundle submission recommendation. It specifies the return values (best builder, inclusion probability, reason) and mentions the optional borrower scope. However, it does not explicitly distinguish itself from the similarly named sibling tool 'get_builder_recommendation', so it stops short of a 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?

The description gives clear usage context: pair with 'monitor_crossing_candidates' after identifying a hot candidate, and use either a specific borrower or current market conditions. It does not explicitly mention when not to use it or name alternative tools, but the workflow guidance is strong enough for a 4.

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.