Inspect and validate an x402 endpoint before an autonomous agent spends USDC.
Scored across 3 tools
Each tool has a clearly distinct role: inspect is free and read-only, audit is a paid deep diagnostic, and order_remediation is a separate purchase flow after an audit. There is no meaningful overlap that would cause an agent to select the wrong tool.
All three tools follow a consistent verb_x402_object pattern: audit_x402_endpoint, inspect_x402_endpoint, and order_x402_remediation. The verbs clearly indicate the action and the naming convention is uniform.
Three tools is an appropriate, focused scope for an x402 preflight server. Each tool represents a distinct stage in the workflow without unnecessary duplication or bloat.
The core workflow is covered: inspect before spending, audit for a deep check, and order remediation after a failed audit. Minor gaps exist around order status or remediation fulfillment, but the essential preflight lifecycle is complete.
Purchase a deep, deterministic audit of payment schema, discovery metadata, redirects, CORS, cache, and operational signals. Returns HTTP 402 until the MCP client supplies a valid payment for this call.
| Name | Required | Description | Default |
|---|---|---|---|
| method | No | GET | |
| resource_url | Yes | Public HTTPS x402 resource to inspect without payment credentials. | |
| max_price_usd | No | ||
| expected_network | No |
| Name | Required | Description |
|---|---|---|
| cors | Yes | |
| score | Yes | |
| checks | Yes | |
| issues | Yes | |
| payment | Yes | |
| profile | Yes | |
| decision | Yes | |
| evidence | Yes | |
| resource | Yes | |
| discovery | Yes | |
| expiresAt | Yes | |
| requestId | Yes | |
| observedAt | Yes | |
| operational | Yes | |
| claimBoundary | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, openWorld, and non-destructive behavior. The description adds the non-obvious paywall behavior: 'Returns HTTP 402 until the MCP client supplies a valid payment for this call.' This is meaningful context beyond the annotations, though the payment mechanics are not detailed.
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 with no filler; the operational 402 behavior is stated crisply. The first sentence is a dense list but still readable 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?
The description covers core purpose and the critical paywall behavior, and the output schema/annotations carry return and safety information. However, it lacks usage guidance and parameter explanations, so it is not fully complete for selecting and invoking 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 only 25% (only resource_url is described), and the description does not clarify method, max_price_usd, or expected_network. The audit-scope list does not map to these parameters, so the low coverage is not compensated.
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 specifies a concrete action (purchase/audit) on a named resource (x402 endpoint) and enumerates the audited areas: payment schema, discovery metadata, redirects, CORS, cache, and operational signals. However, it does not explicitly contrast with inspect_x402_endpoint or order_x402_remediation, so sibling differentiation is left implicit.
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?
No guidance is given for when to prefer audit_x402_endpoint over inspect_x402_endpoint or order_x402_remediation. The only usage-related note is the payment gating condition, which is operational rather than a selection criterion.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Call before spending on an unfamiliar x402 resource. Free, read-only, and never sends payment credentials.
| Name | Required | Description | Default |
|---|---|---|---|
| method | No | GET | |
| resource_url | Yes | Public HTTPS x402 resource to inspect without payment credentials. | |
| max_price_usd | No | ||
| expected_network | No |
| Name | Required | Description |
|---|---|---|
| cors | Yes | |
| score | Yes | |
| checks | Yes | |
| issues | Yes | |
| payment | Yes | |
| profile | Yes | |
| decision | Yes | |
| evidence | Yes | |
| resource | Yes | |
| discovery | Yes | |
| expiresAt | Yes | |
| requestId | Yes | |
| observedAt | Yes | |
| operational | Yes | |
| claimBoundary | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark it read-only and idempotent; the description adds that it is free and never sends payment credentials, which is useful behavioral context beyond the structured hints.
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?
A single, front-loaded sentence with no filler. Every phrase carries meaning, from the trigger condition to the safety guarantees.
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 description provides solid usage context and safety cues, and an output schema exists, but the meaning of optional parameters is left entirely to schema patterns and enums, so completeness is adequate but gapped.
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 descriptions cover only resource_url (25%); the description does not explain method, max_price_usd, or expected_network, so an agent gets no added semantic guidance for three of four parameters.
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 action (inspect an x402 endpoint) and the context (before spending on an unfamiliar resource). It does not explicitly contrast with sibling tools audit_x402_endpoint or order_x402_remediation, so it stops short of full differentiation.
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 an explicit trigger condition ('before spending on an unfamiliar x402 resource') and clarifies that it is free and does not send credentials, but it does not name alternatives or state when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Purchase a durable remediation intake after a failed audit. Creates an order but never deploys, signs, or spends automatically.
| Name | Required | Description | Default |
|---|---|---|---|
| goal | Yes | ||
| contact | No | ||
| language | No | en | |
| constraints | No | ||
| callback_url | No | ||
| resource_url | Yes | ||
| response_format | No | both |
| Name | Required | Description |
|---|---|---|
| review | Yes | |
| status | Yes | |
| orderId | Yes | |
| payment | Yes | |
| request | Yes | |
| service | Yes | |
| acceptedAt | Yes | |
| capability | Yes | |
| persistence | Yes | |
| claimBoundary | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate a write operation (readOnlyHint=false) and non-destructive nature (destructiveHint=false). The description adds crucial context by stating it 'never deploys, signs, or spends automatically', clarifying the boundary of side effects beyond what the annotations convey. It does not, however, describe any required authentication or error behaviors, but the added constraint is valuable.
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 concise sentences that front-load the primary purpose and immediately clarify a critical limitation. Every phrase earns its place with no filler, making it efficient and easy to parse.
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 has seven parameters, two of which are required, and an output schema is present. The description covers the main intent and a key behavioral constraint, but it omits guidance on how to use any of the parameters or what the response will contain (though the output schema covers the latter). Overall, it is adequate for a simple order-creation workflow but leaves parameter semantics under-specified.
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%, meaning the schema properties have no textual descriptions. The tool description provides no explanation of any parameter (e.g., what 'goal' means, how 'constraints' should be formatted, or the purpose of 'callback_url'). The parameter names are somewhat self-explanatory, but the description fails to compensate for the total lack of schema-level documentation, leaving agents to infer semantics from 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 states a specific action ('Purchase a durable remediation intake'), the resource('remediation'), and the context ('after a failed audit'), clearly distinguishing it from sibling tools like audit_x402_endpoint and inspect_x402_endpoint which are involved in auditing/inspection rather than ordering remediation. The clarifying clause 'Creates an order but never deploys, signs, or spends automatically' further narrows its scope.
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 ties usage to the occurrence of a failed audit, giving a clear trigger condition. However, it does not explicitly mention alternatives (e.g., 'use this instead of audit_x402_endpoint when...') nor state when not to use it, so it stops short of full exclusion guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
audit_x402_endpointinspect_x402_endpointorder_x402_remediationCheck an x402 endpoint before your agent pays it: avoid / caution / ok, proven on-chain.
Verify x402 payment endpoints before an AI agent pays: scam scan, on-chain checks, trust scores.
We buy from x402 endpoints with real USDC and publish delivery outcomes. Check before you spend.
Live x402 endpoint trust/diligence check before you pay it. $0.02/call via x402.
Add one secure layer between your agents and this server.
