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

No annotations provided, so description carries full burden. It discloses that the tool returns enriched positions with APY, health factors, and context-specific opportunities. While it doesn't detail side effects (likely none as it's read-only), the description is clear and trustworthy. Minor gap: doesn't explicitly state it's read-only.

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, all informative. The first sentence states purpose and returns, the second gives usage guidance, the third provides workflow integration. Efficient and well-structured. Slight redundancy with 'context-specific opportunities' could be trimmed.

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 simple input (one string) and no output schema, the description fully covers what the tool does, returns, and how it fits into a workflow. No missing information for an agent to use 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 description coverage is 100% for the single parameter 'walletAddress', and the description already implies it's a wallet address. The description adds value by explaining the output is based on what the wallet holds, but the parameter itself is straightforward.

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 analyzes a wallet's DeFi portfolio and surfaces yield opportunities, specifying what it returns (positions, APY options, health factors, opportunities). It uses specific verbs ('Analyze', 'surface') and distinguishes itself from sibling tools like haiku_discover_yields and haiku_execute.

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 states when to use ('when a user asks what they should do with their portfolio or wants yield optimization advice') and provides clear guidance on pairing with haiku_discover_yields for market context and haiku_get_quote for execution. No exclusions needed.

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?

No annotations provided, so description carries full burden. It discloses that results include APY, TVL, risk parameters, and token IIDs, and that the iid field is usable in haiku_get_quote. However, it does not mention rate limits, pagination behavior, or response size limits beyond the 'limit' parameter.

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?

Concise at three sentences. The first sentence states purpose, second lists outputs and downstream use, third provides examples. Every sentence adds value. Slightly verbose in the last sentence with multiple examples, but 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 6 parameters with 100% schema coverage and no output schema, the description effectively explains the tool's purpose and output semantics. It could be improved by describing the risk parameters' nature (e.g., risk score vs. qualitative), but overall adequate.

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 value by explaining the iid field's downstream use and by including example questions. However, it does not add new meaning beyond the schema for most parameters, as the schema already has clear descriptions for each.

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 discovers yield opportunities across DeFi protocols and lists specific output fields (APY, TVL, risk parameters, token IIDs). It distinguishes itself from siblings like haiku_get_quote by explaining the iid output can be used as input for that 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?

Provides explicit example questions for when to use the tool, such as 'best lending yields on Arbitrum' or 'highest APY vaults with at least $1M TVL'. It also explains how the output connects to haiku_get_quote, guiding the agent on downstream 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?

No annotations provided, so description carries full burden. It fully discloses the tool's behavior: two distinct execution modes, signing internal vs external, broadcasting behavior (broadcast: true/false), and the transaction output format (tx hash vs { to, data, value, chainId }). No contradictions with annotations since none exist.

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 well-structured with bullet points for two clear paths, front-loading the main purpose. Every sentence adds value with no redundancy. Length is appropriate for the 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 8 parameters with 100% schema coverage, no output schema, and high complexity (two modes, nested objects), the description fully covers usage flow, parameter dependencies, and return format for both paths. No gaps identified.

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 baseline is 3. The description adds significant value beyond schema by explaining when each parameter is needed (e.g., approvals in self-contained vs external mode, permit2SigningPayload vs permit2Signature based on path). The 'broadcast' parameter's effect is clarified. Minor deduction for not detailing the nested objects' structure (e.g., approval {to, data}) beyond what schema provides.

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 'Execute a quote' and distinguishes two paths (self-contained vs external wallet), which differentiates it from sibling tools like haiku_get_quote or haiku_prepare_signatures. The verb 'execute' plus resource 'quote' is specific and 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 provides explicit step-by-step instructions for both Path A and Path B, including when to call haiku_get_quote first, when to use haiku_prepare_signatures, and when to broadcast approvals via wallet MCP. It clearly states alternatives and when not to use certain parameters.

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?

With no annotations provided, the description must disclose behavioral traits. It explains optional wallet address derivation from environment variable and the partial refresh behavior. However, it doesn't mention rate limits, data freshness, or what happens if the wallet address is invalid. Adequate but not comprehensive.

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 a clear structure: first sentence states purpose, second elaborates on parameters and return values. It is front-loaded and efficient, though the list of chain IDs could be trimmed.

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 no output schema, the description explicitly lists return fields (balances, USD prices, portfolio value, categories). It covers the two parameters well. For a simple query tool, this is complete enough. Missing details about error handling or data freshness, but acceptable.

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 significant value by explaining the partial refresh use case for chainIds, providing common chain IDs and examples. For walletAddress, it clarifies optionality and auto-derivation. This goes beyond schema 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 states the tool retrieves token balances for a wallet address. It specifies the default behavior (all chains) and contrasts with a common variant (partial refresh with chainIds). This distinguishes it from siblings like haiku_analyze_portfolio which likely provides deeper analysis rather than raw balances.

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 explains when to use the tool (get balances) and when to use the chainIds parameter (after a swap for faster partial refresh). It doesn't explicitly exclude other scenarios or mention alternatives among siblings, but the context is clear.

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?

No annotations are provided, so the description carries full burden. It transparently explains that the tool returns EIP-712 signing payloads when signatures are required and outlines the two execution paths. However, it does not disclose potential side effects, rate limits, or authorization requirements beyond the receiver field note.

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 well-structured with bullet points for the two execution paths, making it easy to parse. It is slightly verbose due to the detailed path explanations, but every sentence adds value and avoids 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?

Given the tool's complexity (nested objects, multiple execution paths, no output schema), the description covers the key aspects: what the tool returns, how to proceed after getting a quote, and parameter details. However, it could be improved by mentioning that no output schema exists, so the agent must infer the response structure.

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 baseline is 3. The description adds value by explaining the IID format and providing examples for inputPositions and targetWeights, as well as clarifying the receiver parameter's behavior based on private key presence. However, it does not elaborate on slippage beyond its default 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 fetches a quote for token swaps or portfolio rebalances, listing expected outputs like fees, gas estimates, and required approvals. It also distinguishes this tool from siblings by detailing its role as the first step in a multi-tool execution flow.

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 guidance on when to use this tool (before execution) and details two distinct execution paths (Path A with private key, Path B with external wallet) including step-by-step instructions and sibling tool names like haiku_execute and haiku_prepare_signatures.

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?

No annotations provided, so description carries full burden. It discloses that the tool returns token IIDs, symbols, names, prices, and chain information, and explains the IID format. However, it doesn't mention if this is a read-only operation, potential rate limits, or any side effects.

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 with 4 sentences, front-loading the main purpose. Each sentence adds value. Could be slightly shorter by removing redundant 'Use the IID format' since schema already describes it, but 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 has 2 optional parameters and no output schema, the description adequately explains purpose, return data, and usage guidance. The context signals show low complexity, and the description is sufficient for an AI agent to invoke 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 both parameters having detailed descriptions. The description adds context beyond schema by listing token types and explaining IID format. The enum values are also clarified in description, but schema already covers them.

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 supported tokens and DeFi positions for trading, listing specific types like vanilla tokens, Aave collateral/debt, yield vaults, and LP tokens. This differentiates it from siblings like haiku_get_balances (balances) and haiku_analyze_portfolio (portfolio analysis) by focusing on supported token metadata.

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 explains when to use category filter and gives an example ('collateral' for Aave aTokens). It also instructs to use IID format in other tools. However, it does not explicitly state when not to use this tool or compare to alternatives like haiku_get_balances for balances.

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?

Since no annotations are provided, the description must disclose behavior. It explains that the tool extracts/normalizes EIP-712 payloads and does not execute the transaction, which is crucial. It also indicates it's a read-only preparation step, not destructive. However, it doesn't mention any authorization requirements or side effects, but given the tool's nature (signature preparation), the description is largely transparent.

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 and efficiently conveys purpose, usage, and parameter guidance. It could be slightly more concise by removing the last sentence about post-signing steps (which might belong in haiku_execute's description), but overall it's well-structured and front-loaded.

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 no output schema, the description implicitly covers return values (normalized EIP-712 payloads). It addresses the tool's role in a multi-step process (sign then execute). It lacks detail on the output format or error cases, but for a preparation tool with two optional params, it is reasonably 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?

Schema description coverage is 100%, so the schema already documents both parameters. The description adds value by explaining the preferred parameter (quoteId) and fallback (quoteResponse), and clarifying that quoteId allows server-side resolution from session cache. This goes beyond what the schema provides, justifying a score above 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 the tool's purpose: preparing EIP-712 signatures for external wallets, distinguishing it from haiku_execute. It specifies the resource ('EIP-712 payloads from a quote') and the action ('extracts and normalizes'), making it distinct from siblings.

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 this tool (when WALLET_PRIVATE_KEY is not set or wallet MCP handles signing) and when not to (instead of passing directly to haiku_execute). It also provides guidance on which parameter to use (prefer quoteId, fallback to quoteResponse), and what to do after ('pass permit2Signature and/or userSignature to haiku_execute').

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