Scan agent payment endpoints (x402, AP2, L402, MPP, 402) for a trust grade A-F before paying.
Scored across 2 tools
Each tool has a clearly distinct purpose: one verifies a specific 402 offer at spend time, the other scans an endpoint for a safety grade before paying. No overlap.
Both tools follow the same 'attest_' prefix with a verb (guard, scan), creating a predictable pattern.
With only 2 tools, the set is slightly small but appropriate for a focused payment verification utility; each tool serves a distinct and necessary step.
The two tools cover the core workflow of scanning an endpoint and verifying an offer. Minor gaps (e.g., historical checks) exist but the surface is adequate for the stated purpose.
Verify a live 402 payment offer at the moment of spend. Pass the EXACT offer you just received (url, payTo, amount, asset, network) and get an allow / warn / block verdict with machine-readable reasons: wallet mismatch vs the verified payout wallet, price swaps vs the last verified quote, danger flags, blocklisted wallets, and typosquats. Call this AFTER receiving a 402 offer and BEFORE authorizing the payment.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The endpoint URL you are about to pay. | |
| asset | Yes | Asset contract address or symbol from the offer. | |
| payTo | Yes | The payout address presented in the live 402 offer. | |
| amount | Yes | The offered amount in atomic units, as a string. | |
| scheme | No | Optional payment scheme (e.g. exact). | |
| network | Yes | Network / chain identifier from the offer (e.g. base, solana). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Describes return verdict types (allow/warn/block) and reasons (mismatch, swaps, flags, blocklists, typosquats). No annotation provided, so description carries full burden; it does well but could mention if it mutates state (likely not).
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 purpose, no redundancy. Every word adds value.
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 no output schema, description explains return value format. Covers when to use, what to pass, and expected output for a 6-parameter tool with full schema coverage.
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% but description adds vital context: 'Pass the EXACT offer you just received', ensuring precise use. Also clarifies 'scheme' as optional beyond schema.
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 verifies a live 402 payment offer, with specific verb 'verify' and resource 'offer'. It distinguishes from sibling 'attest_scan' by focusing on spend-time verification.
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 says 'Call this AFTER receiving a 402 offer and BEFORE authorizing the payment', providing clear temporal context. Lacks explicit mention of when not to use or alternatives, but sibling context is implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Scan an agent payment endpoint (x402 / HTTP 402) and return a letter grade A to F with a safety verdict before paying.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The endpoint URL to scan. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It mentions the return (grade and verdict) but does not disclose side effects, idempotency, or safety implications beyond the scan result. Moderate transparency.
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 that efficiently conveys purpose, resource, output, and usage timing. 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?
Given the tool's simplicity (1 param, no output schema), the description adequately covers purpose, input, and output. Minor gap: could mention whether the scan is safe or verbose, but overall 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% with a clear parameter description. The tool description does not add additional meaning or constraints beyond the schema, so 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 specifies the action (scan), the resource (agent payment endpoint with x402/HTTP 402 context), and the output (letter grade A-F plus safety verdict). It clearly distinguishes the tool's purpose.
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 'before paying' which implies when to use. However, it does not provide exclusions or alternatives, though no sibling tools exist. 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.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
attest_guardattest_scanVerify x402 payment endpoints before an AI agent pays: scam scan, on-chain checks, trust scores.
Pre-payment merchant trust checks for x402 agents on Base and Solana.
Verified directory for machine payments (x402 & MPP): check services and wallets before agents pay.
The honest trust index for x402: check who you're paying before your agent pays.
Add one secure layer between your agents and this server.
