onramperx

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

Annotations already provide readOnlyHint=true; description adds specific context about fee collection comparison, but does not disclose other traits like error handling or auth needs.

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?

Single sentence is concise, front-loaded with action and resources, 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?

Description covers purpose and key check items, but lacks output format details; no output schema means agent lacks expected 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?

Single parameter requestId is explained as the swap identifier, adding some meaning beyond schema, but description does not provide format or constraints.

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?

Clearly states the verb 'check' and resources 'status' and 'fee collection', but does not explicitly differentiate from sibling tools like get_route_quote or create_swap.

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 usage context ('Use this to check...') but does not mention when not to use or alternative tools.

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 key behavioral traits: the need for human interaction ('fiat legs cannot be programmatically triggered'), user notification, and limits ($500/week, US-only). With only openWorldHint annotation, this description adds valuable context beyond the structured fields.

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, front-loaded with purpose, and efficient. Every piece of information is relevant and earns its place.

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 3 parameters, no output schema, and minimal annotations, the description adequately covers the tool's purpose, usage context, critical behavioral requirement (human tap), and constraints. It could mention the return value type (URL) but overall is 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?

With 0% schema description coverage, the description adds meaning for amountUsd (max $500/week) and geo (US-only implied), but does not explain destinationAddress or the optional geo parameter further. Coverage is partial.

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 verb 'buy', the resource 'USDC on Base', and the payment methods (card/Apple Pay/Google Pay). It also specifies the target user (US) and constraints ($500/week), effectively distinguishing it from siblings like create_swap which likely handle token swaps.

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 says 'Use this when a US user wants to buy USDC on Base' and notes that 'a HUMAN must physically tap', providing clear context for when this tool is applicable. However, it does not explicitly state when not to use it or mention 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?

The description adds some behavioral context beyond the openWorldHint annotation by stating 'Returns a headless deposit address (no signing) or an on-chain intent' and 'App fees accrue on swaps.' However, it does not disclose error scenarios, timeouts, or the implications of the 'headless deposit address' feature.

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 at two sentences, front-loading the primary purpose. However, it could be slightly improved by including a brief note on required parameters without significantly increasing length.

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 (4 required) and no output schema, the description fails to explain key concepts like 'headless deposit address' vs 'on-chain intent' or the necessity of a prior route quote. The agent lacks sufficient information to correctly invoke the tool without external knowledge.

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 0% schema description coverage, the description must compensate but only vaguely references fromToken and fromChain. It does not explain crucial parameters like amount (unit/format), recipient (wallet address?), humanPresent (meaning), or toChain (optional but not described). The agent is left to guess from parameter names alone.

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: 'swap any token on any chain into USDC on Base via Relay.' It specifies the action (swap), the resource (tokens into USDC on Base), and distinguishes from sibling tools like check_swap (status) and get_route_quote (quotes).

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 only states when to use the tool ('Use this to swap...') but provides no guidance on when not to use it or how it relates to siblings. For example, it doesn't mention that get_route_quote should be called first to obtain a quote, or that check_swap can be used afterward to monitor progress.

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 readOnlyHint and openWorldHint. The description adds transparency by detailing the output (ranked rails with fees, ETA, KYC burden, limits, reasoning) and specifying non-custodial nature. No contradictory information.

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, using two sentences to convey purpose and output. It is front-loaded with usage intent. However, it could be structured with bullet points for easier parsing.

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 7 parameters (3 required) with nested objects and no output schema, the description covers the tool's purpose and output but lacks input field semantics. Annotations help, but more detail on source/destination structure would improve completeness.

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 0%, but the description provides no explanation of parameters like geo, speed, source, destination, etc. It only describes output fields. With no parameter details, it gives minimal help for correct invocation.

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: providing the best non-custodial way to move value between fiat and crypto or crypto to crypto, returning ranked rails with detailed information. It distinguishes from sibling tools like check_swap or create_swap by focusing on quoting rather than execution.

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 says when to use it ('when a human or agent wants the best non-custodial way to move value'). It provides context but does not explicitly state when not to use it or compare with sibling tools, though the intent to get a quote 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?

Annotations include only openWorldHint=true, which is reinforced by the description's mention of 'gasless' and 'non-custodial'. The description adds behavioral details (TEE keys, user-exportable) beyond annotations, but omits potential side effects like existence of previous wallets or cost implications.

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 sentence that front-loads the action and key attributes. Every phrase adds value, and there is no redundant or verbose language.

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 (1 param, no output schema), the description covers the essential purpose and behavioral traits. However, it does not describe the return value (e.g., wallet address or confirmation), leaving ambiguity about the tool's output. With no output schema, this is a notable 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?

The only parameter, 'owner', is a string with 0% schema coverage. The description does not explain what 'owner' represents (e.g., user ID, email, or wallet address) or provide any format/constraints. With no parameter documentation in the schema, the description should compensate, but fails to do so.

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 action (create), resource (gasless CDP Embedded Wallet), network (Base), and key traits (non-custodial, TEE keys, user-exportable). Sibling tools are all different operations (swap, onramp, quote), so purpose is unambiguously distinct.

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 states when to use the tool (to create a wallet for receiving routed value) but does not provide explicit when-not-to-use guidance or mention alternative tools. However, the context is clear and sufficient for basic selection.

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