El juicio de una persona real (no un LLM) por $0.10 USDC en Base. Vía Telegram.
Scored across 2 tools
The two tools have clearly distinct roles: ask_human_verdict creates a request and get_human_verdict retrieves the result. There is no overlap or ambiguity between them.
Both tools follow a consistent verb_noun pattern (ask_human_verdict, get_human_verdict), making the API predictable and intuitive.
With only 2 tools, the server is minimal but appropriately scoped for its specific purpose (requesting and polling a human verdict). The thin count is justified by the narrow domain, though it could be seen as slightly sparse.
The tool surface covers the core lifecycle: creating a request and polling its status. There is no explicit cancel or update operation, but the 7-day expiry handles abandonment, making the workflow complete for its intended use.
Pagá $0.10 USDC en Base por el juicio subjetivo/cultural de una persona real (no un LLM) sobre una pregunta — especializado en contexto argentino. Sin pago adjunto devuelve los requisitos de pago x402; con el pago, crea el ticket y devuelve {ticket, resultToken, poll}. La respuesta del humano llega de forma asíncrona — usá get_human_verdict para pollear.
| Name | Required | Description | Default |
|---|---|---|---|
| labels | No | CSV de 2-6 respuestas categóricas posibles, ej. "natural,traducido" | |
| context | No | Contexto extra que ve el humano | |
| question | Yes | La pregunta de juicio subjetivo |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the paid nature ($0.10 USDC on Base), the conditional behavior based on attached payment, the returned object shape ({ticket, resultToken, poll}), and asynchronous delivery. It doesn't cover payment attachment mechanics or failure modes, but it is substantially 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 with no filler. It front-loads the payment/cost, then the mode-dependent behavior, then the async handoff. Every sentence 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?
Despite having no output schema and no annotations, the description covers the core flow: payment requirements, ticket creation, returned keys, async nature, and the polling sibling. The only notable gap is not explaining how payment is actually attached (x402 mechanics), which is a minor omission for a paid 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 description coverage is 100%, so the baseline is 3. The description adds general context about labels being CSV and context being visible to the human, but it doesn't meaningfully extend parameter semantics beyond what the schema already 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 identifies a clear verb+resource: 'Pagá ... por el juicio subjetivo/cultural de una persona real', and emphasizes it is not an LLM and is specialized for Argentine context. It also differentiates from the sibling get_human_verdict by describing this tool as creating the ticket while the sibling polls for results.
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 the two payment modes (no payment returns x402 requirements; with payment creates the ticket) and explicitly instructs to use get_human_verdict for polling after the async response. It doesn't state formal when-not-to-use criteria, but the async handoff is clearly communicated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Gratis. Pollea el estado de un ticket creado con ask_human_verdict — "pending" mientras la persona todavía no contestó, "completed" con el veredicto, o "expired" si pasaron 7 días sin respuesta.
| Name | Required | Description | Default |
|---|---|---|---|
| ticket | Yes | El ticket devuelto por ask_human_verdict | |
| resultToken | Yes | El resultToken devuelto por ask_human_verdict |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the burden. It does disclose the polling behavior and the meaning of each status, adding value beyond the schema. However, it doesn't mention the cost of polling (it says 'Gratis' but not rate limits), how to handle errors (e.g., invalid ticket), or whether it's a read-only operation. Still, the core behavioral traits are covered.
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 one sentence that is concise and front-loads the key information (Gratis, polls). It clearly explains the states without fluff. Every word 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?
For a simple polling tool with two parameters and no output schema, the description covers the essential behavior: states and their meanings, and the expiration. It could add a note on error handling or what happens if the ticket is invalid, but given the simplicity, it's nearly 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 fully documents both parameters (ticket and resultToken). The description adds context by stating they come from ask_human_verdict, but doesn't add additional syntax or format details. 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 clearly states the tool polls the status of a ticket and lists the three possible states (pending, completed, expired) with meanings. It specifies the resource (ticket from ask_human_verdict) and the verb (pollea). It distinguishes itself from its sibling by focusing on querying, not creating.
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 it is for polling a ticket created by ask_human_verdict and describes the states and the expiration period. This provides clear context for when to use it versus the sibling, which is for creating the ticket. It also implies it's for checking results after creation.
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.
ask_human_verdictget_human_verdictPayPerByte — per-byte data for AI agents: x402 USDC on Base, EIP-712-attested. No token.
AI LLM with Gemini, MiniMax, Replicate, OpenRouter. Vision, search, code review. USDC on Base.
Pay-per-call LLM chat plus data tools: DNS, crypto, Base gas, Wikipedia. x402 USDC or Lightning.
Agents pay for work and prove it. Verified checks $0.15, recovery $1.00. USDC on Base via x402.
Add one secure layer between your agents and this server.
