Vurto Swap

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

Annotations only note non-readOnly, openWorld, non-idempotent, non-destructive. The description goes beyond by disclosing that the two legs are NOT atomic, that each is a separate transaction/signature, and the critical sequencing requirements. It also explains the risk of proceeding if leg A fails, which is crucial behavioral context.

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 a single dense paragraph with no bullets, but it's reasonably concise and information-dense. It front-loads the core message (builds both legs) and includes important warnings. However, it could be better structured with visual breaks for the execution sequencing guidance, but it's still efficient.

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 (nested objects, multiple legs, non-atomic behavior) and lack of output schema, the description covers key aspects: what it does, the non-atomicity, and execution order. It lacks details on error handling and edge cases, but those might be overkill. The presence of sibling tools like swap_build lets an agent infer comparison. Overall, it's well-covered for an agent to call 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 60%, with legA and legB having detailed inner property descriptions (amount vs amountRaw, receiver conditions, Solana nuances). The description adds a global maxSlippageBps applying to both legs and the alias semantics for legA/legB, but these are mostly covered by schema descriptions. The description doesn't add significant new parameter meaning beyond what's in the schema, so a 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 builds plans for both legs of a Double Out or Double In swap, wrapping two swap_build calls, and explicitly differentiates it from ordinary swap_build by noting the convenience wrapper and the separate legs. It also specifies the return shape ({ legA, legB }), which isn't in the schema.

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 explicit instructions: execute leg A fully and confirm it landed before starting leg B, and do NOT execute leg B if leg A fails. It also references sibling swap_build as the underlying mechanism, distinguishing this tool. No explicit alternatives are given, but the context makes it clear when to use this vs a single swap.

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, but the description adds substantial behavioral context: it is two independent quotes, not an atomic route; it does not compute splits/percentages; and it warns about double gas for native assets. These go beyond the structured annotations and meaningfully shape how an agent should invoke and interpret the tool.

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 thorough but every sentence earns its place: it covers purpose, rationale, non-atomicity, mode-specific constraints, amount responsibility, and a gas caveat. It is front-loaded with the core functionality before diving into constraints. It could be slightly tightened, but the length is justified by the tool's complexity.

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 (two nested leg objects, multiple modes) and the absence of an output schema, the description covers the essential invocation logic and key caveats. It does not describe the exact output shape, but it states each leg is independently quoted, giving a reasonable expectation. The description is sufficiently complete for correct invocation, with minor room for output-format 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?

Schema coverage is 60%, so the schema already documents many parameters. The description adds critical relational semantics not in the schema: for mode 'out' legA.tokenIn must equal legB.tokenIn, and for mode 'in' legA.tokenOut must equal legB.tokenOut. It also clarifies that amounts are exact and not split, which directly affects parameter usage. This goes beyond the schema's per-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 states a specific verb ('compares ranked routes') and a distinct resource (two swap legs at once), and explicitly names the two modes (Double Out / Double In). It distinguishes itself from a single swap_quote by stating it is 'two ordinary swap_quote calls under the hood,' so an agent can tell it apart from siblings like swap_quote and double_build.

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 when-to-use context: it exists for 'building a liquidity pool or matching a target ratio' where both legs must be priced simultaneously. It also clarifies it is not a combined/atomic route, which implicitly warns against expecting atomicity. However, it does not explicitly name alternatives or exclusions (e.g., 'use double_build for the actual build'), so it falls just 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?

The description discloses critical behavior beyond the minimal annotations: no quoteId handoff, fresh re-quoting, optional machine credential rate-limit effects, approve-step targeting of VurtoSwapRouter rather than underlying providers, approval_required simulation flow, routeSwitch fallback semantics, and unsupported status endpoints. This is far more than the annotations alone provide.

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 long, but the complexity of the tool justifies the length. It is front-loaded with the core purpose and organized around major behavioral topics (quoting, auth, steps, routeSwitch, status). A few sentences are slightly redundant, such as the repeated no-quoteId point, but no sentence is 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?

With no output schema, the description fully explains the return shape (steps[] with approve steps and one transaction step), the approval flow, the routeSwitch replacement behavior, and the correct post-send verification path. It covers auth, prerequisites, and error/fallback conditions, leaving no critical gap for an agent to call it 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 moderate at 60%, and the description adds contextual meaning by tying chainId/inputLegs/outputLegs to the fresh re-quote behavior and by explaining that wallet is the signing wallet. It does not walk through every parameter, but the schema already documents the individual fields, and the description clarifies how they are used together.

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 and resource: 'Builds ONE signable/sendable atomic transaction executing every leg of an N:N basket through VurtoSwapRouter.' It clearly distinguishes itself from related tools by emphasizing the N:N basket scope, the absence of quoteId handoff, and the contrast with swap_build's per-provider approvals.

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 gives explicit when-to-use guidance: pass the same fields as nn_quote or skip nn_quote and call directly, and no API key is required. It also states when not to use supporting tools: report_execution and swap_status do not support this build's transaction step, so the agent should check the receipt directly.

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 valuable behavioral context: the waterfall allocation, the atomicity, the fact that failures[] can result in a partial basket that is 'never silently dropped,' and the relationship to nn_build (legs are what will be executed). It also discloses chain-specific failure modes (multi_swap_not_supported_on_chain) and Solana's runtime all-or-nothing rule. This goes well 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 dense but every sentence earns its place: it defines the tool, explains the allocation, gives the outputPercent constraint, states limits, and describes the return shape. It is longer than average, but the complexity of the tool justifies the length. The most critical differentiator (NOT decomposable) is front-loaded early. Slight redundancy exists between the schema's outputPercent description and the tool description, but that is minor.

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 complex N:N quoting tool with no output schema, the description does a strong job: it explains the return shape (legs[] with NormalizedQuote, failures[]), the partial-basket behavior, the leg count bound, and the chain-specific constraints. It does not detail pagination or exact failure error formats, but those are less critical for a quote tool. The annotations cover safety, and the schema covers parameters. The description is complete enough 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?

Schema coverage is 60%, so the description carries some burden. It adds meaning to inputLegs[] and outputLegs[] by explaining the allocation semantics: outputPercent is 'an integer percent of the TOTAL basket value, not a fixed amount, because the actual split depends on the allocation.' It also clarifies the leg count limit and the resulting on-chain leg count formula. The wallet parameter is not discussed in the description, but the schema already covers it well. The description compensates for the schema's gaps on the core basket semantics.

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 precise definition: 'N:N — quotes a basket where N input tokens fund M output tokens in ONE atomic on-chain transaction.' It names the specific verb (quotes), the resource (a basket), and the key differentiator (atomic, waterfall allocation). It also explicitly contrasts with swap_quote/double_quote, making sibling differentiation clear.

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 states when NOT to use this tool: 'NOT decomposable into independent swap_quote/double_quote calls — the allocation itself is the thing being computed.' It also explains the outputPercent constraint and the partial-basket behavior, giving an agent clear conditions for invocation. The sibling list includes swap_quote and double_quote, and the description directly addresses why those alternatives are not equivalent.

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?

Beyond the readOnlyHint and idempotentHint annotations, the description discloses critical behavior: the command blocks until user approval/rejection/timeout, prints one JSON line, and exits; expected_keys tells which result field to read; Solana returns a different signer with the same shape and requires POSTing to /v1/svm/execute. This is rich, non-obvious behavioral context that annotations alone would not provide.

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 long but every sentence carries high-signal operational detail. It is front-loaded with the core purpose, then flows into agent instructions, EVM behavior, and Solana behavior. There is no filler or repetition of schema content.

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 having no output schema, the description fully explains the return behavior: one JSON line, expected_keys values (txHash, signature, signedTransaction), and the follow-up POST for Solana. It also covers blocking behavior, chain-specific differences, and the private-key handling rule, making it complete for a complex 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%, so the baseline is 3, but the description adds meaningful parameter semantics: it explains EVM step types (approve/transaction/signature), Solana's lack of steps[] and approve, the exact step shape to pass for Solana, and the significance of executionRef absence. This goes beyond the schema's field-level 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 states a specific verb and resource: it 'synthesizes the local CLI signer invocation for one step of a swap_build plan' and explicitly distinguishes itself by noting it 'does not call the Vurto backend'. This clearly separates it from backend-calling siblings and makes its role 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 operational guidance: the agent must not ask for a private key, should run the command as a background task, and should never ask the user 'did you sign?'. It also clarifies when EVM vs Solana parameter shapes apply. It does not name sibling tools as alternatives, but the context is clear enough for correct use.

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 annotations by disclosing server-side behavior: the server reloads the stored build, submits the signed CoW order, returns a uid, verifies the Solana fee payer/transaction, and has no transaction hash for the CoW path. It also clarifies credential behavior, adding real context without contradicting 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 dense but every clause earns its place. It front-loads the purpose, then gives three compact path-specific sentences and a final credential note, with no filler or repetition.

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 multi-path, 6-parameter tool with no output schema, the description covers parameter routing, server-side effects, auth, and the CoW path's uid return. It stop short of describing return or error semantics for the EVM-transaction and Solana paths, which is a minor but real gap.

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 the baseline is 3, but the description adds crucial cross-parameter relationships: wallet + txHash + quoteId for EVM, wallet + chainId + quoteId + signature for CoW, and buildId + signature for Solana. This combinatorial guidance is not visible in the flat schema and meaningfully helps an agent assemble correct calls.

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 'Reports a completed swap, closing the loop,' which clearly names the action and resource. It then details three distinct invocation paths (EVM transaction, EVM CoW signature, Solana), making it easy to distinguish from sibling build/quote/status 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?

The description gives precise parameter combinations for each execution path and an explicit exclusion: 'never report an approve step as an execution.' It also notes that no API key is required. It does not explicitly name sibling alternatives like swap_status, but the path-specific guidance is strong enough to route correct usage.

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?

Discloses behavioral traits far beyond the annotations: ordered/required steps, revert risk from skipping an approve, simulation.status handling for approval_required and incomplete, signature-step semantics, cowswap order-registration caveat, and routeSwitch replacement. These are critical execution details the annotations (readOnlyHint, destructiveHint, etc.) do not convey.

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 long but front-loads purpose and organizes the remaining material into five numbered, scannable behavioral points. Each sentence carries a necessary warning for a complex execution tool, though the overall length sits near the upper bound.

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 of a multi-step swap execution, rich schema coverage (100%), and no output schema, the description covers the critical edge cases: simulation statuses, ordered steps, cowswap registration, and route switching. An agent has enough information to invoke and sequence 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 description coverage is 100%, and the schema already documents every parameter in detail. The description reinforces quoteId and wallet behavior but adds no new syntax, constraints, or parameter meaning beyond what the structured schema provides. 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?

States a specific verb and resource (build a signable/sendable swap plan) and explicitly distinguishes itself from swap_quote by describing when it quotes fresh versus building a prior route. An agent can tell this is the end-to-end execution builder, not just a quoting 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?

Gives explicit when-to-use guidance: omit quoteId to quote-and-build in one call (recommended), pass quoteId from swap_quote to pin a route, and call swap_build again with quoteId after an approval_required result. It also names swap_status as the way to learn what actually happened, covering when not to rely on a receipt.

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 annotations' readOnly and non-destructive hints. It reveals that no spend occurs, explains the ranking is by net value after gas and platform fees rather than raw output, discloses the single unit price behavior, explains estimatedGas vs gasUsd, and highlights a critical time-sensitive behavior: quoteId is only valid for 10-12 seconds and must not be held. This is rich behavioral context an agent needs beyond what annotations provide.

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 dense but efficient: each sentence earns its place. It leads with the purpose and read-only nature, then explains ranking logic, gas detail, and the critical expiration behavior. No filler or redundancy is present, and the most operationally important warning about quote lifetime is placed at the end where it builds on the previous context.

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 quote tool with no output schema, the description covers the essential behavior: what the quote compares, how routes are ranked, how fees and gas factor in, and the short-lived validity of quoteId. It also routes to the next step (swap_build) and warns against stale quotes. When combined with the fully documented input schema, the definition is complete enough for an agent to invoke this 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 description coverage is 100%, so the input schema already documents all 8 parameters thoroughly, including chainId types, tokenIn symbols and mint behavior, amount vs amountRaw, receiver constraints, and slippage. The description does not need to add parameter-level meaning and mostly reinforces behavioral concepts like quoteId and gas rather than explaining params. Baseline 3 is appropriate because the schema carries the load.

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 and object: 'Compare ranked routes across providers for a swap,' which clearly identifies the tool's job. It also distinguishes the quote step from building by saying 'without building or spending anything' and references swap_build as the consumer. It does not explicitly differentiate from sibling quote tools like double_quote or nn_quote, but the 'across providers' framing and comparison emphasis provide enough clarity.

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 makes the usage context clear: call this before building or spending, and use the returned quote as input to swap_build. It also gives explicit temporal guidance not to hold a quoteId because quotes expire in 10-12 seconds and to quote again instead. It does not systematically state when NOT to use this tool versus the other quote siblings, so it stops short of full alternative-comparison 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?

Annotations already mark the tool read-only and idempotent; the description adds meaningful behavioral detail: for CoW ETH-flow it consults the orderbook and distinguishes order_expired_refundable from order_expired_refunded (rather than trusting the receipt), and for Solana it lists the possible network statuses (confirmed, pending, failed, expired). This goes beyond the 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?

Two well-organized sentences with no fluff. The core purpose is front-loaded ('Re-checks a swap'), and the EVM/Solana split is clear and scannable. Every clause adds value; nothing is redundant.

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?

The tool handles multiple chains and optional parameters, yet the description explains the chain-specific inputs and even hints at possible outcomes (statuses for Solana, distinguishing expiry types for CoW). With no output schema, it gives enough about the expected return behavior. It doesn't describe the exact return structure, but for a status-check tool this is sufficient.

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%, giving a baseline of 3. The description adds cross-chain usage context: it specifies which parameters apply to which chain (wallet+executionId for EVM, signature for Solana), and clarifies that executionId comes from report_execution. This is additional meaning beyond the schema's per-parameter descriptions, which are more generic.

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 ('Re-checks a swap') and immediately separates EVM and Solana variants, clarifying that this is a status-check tool distinct from the build/quote/execution siblings. It even names the source of the executionId (report_execution), which disambiguates it from that 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?

It explicitly tells the agent which parameters to pass for each chain ('EVM: pass wallet + executionId', 'Solana: pass signature') and references report_execution as the source of the id, implying this tool is used after execution to re-check status. It doesn't explicitly say 'use this instead of X', but the contextual guidance is clear enough given the sibling names.

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