AI infrastructure claim verification & CAPTCHA solving via x402 pay-per-query
Scored across 8 tools
Most tools have clearly distinct purposes: probing health, fetching raw HTML, extracting structured JSON, reading clean markdown, searching, solving captchas, and verifying claims. The three web-fetching tools (fetch_stealth_web, read_web_page, extract_json_from_web) could be confused, but their descriptions and 'when NOT to use' guidance effectively separate them.
All tool names follow a snake_case verb-first style (check, extract, fetch, get, read, search, solve, verify), which is predictable. There are minor inconsistencies in how 'web' is positioned (search_web vs read_web_page vs fetch_stealth_web), but the pattern remains readable and coherent.
Eight tools is a well-scoped size for a web verification/scraping/captcha-solving toolkit. Each tool covers a distinct step in the workflow—search, fetch, read, extract, probe, verify, and captcha handling—so none feel redundant or missing.
The toolkit covers the core lifecycle of web research and verification: discovery (search_web), retrieval (fetch_stealth_web/read_web_page), extraction (extract_json_from_web), validation (check_endpoint_health, verify_ai_claim), and bot-wall circumvention (solve_captcha). Minor gaps exist around binary file handling and heavy interactive page automation, but these are explicitly out of scope and don't create dead ends.
Probe and verify the reachability, HTTP status code, latency, and operational health of an AI API endpoint or web service. Follows redirects with a 15-second timeout. Requires x402 micropayment (0.01 USDC on Base).
When to use: Check if a specific API URL or model endpoint is online, responding, or returning 5xx/402 errors. When NOT to use: Do NOT use for general domain WHOIS or DNS record lookups.
Parameters:
url (string, required): Target HTTP/HTTPS endpoint URL to probe (8-1000 chars), e.g. 'https://api.openai.com/v1/models'.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The target API or service endpoint URL to probe. |
| Name | Required | Description |
|---|---|---|
| verdict | Yes | Reachability status verdict |
| checked_at | No | ISO 8601 timestamp of the check |
| latency_ms | Yes | Response latency in milliseconds |
| http_status | Yes | HTTP status code returned by the target endpoint |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the tool as read-only and idempotent, and the description adds meaningful behavioral context: follows redirects, enforces a 15-second timeout, and requires an x402 micropayment of 0.01 USDC on Base. No contradiction exists between the description and annotations.
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, front-loaded with the core purpose, and every section earns its place: overview, behavioral specifics, usage guidance, and parameter note. It is concise without omitting critical operational details.
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 only one parameter, an output schema, and strong annotations, the description covers all essential call context: what the tool checks, timeout/redirect behavior, payment prerequisite, and when it should not be used. No critical information is missing for an agent to invoke 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 coverage is 100% and the single `url` parameter is already well-documented with format, examples, and length constraints. The description adds marginal emphasis on HTTP/HTTPS and repeats the character range, but does not substantially extend schema semantics.
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 tool's specific function: probing and verifying reachability, HTTP status, latency, and operational health of an API endpoint or web service. It differentiates itself from sibling web/content tools by focusing on endpoint health rather than content extraction or searching.
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?
Explicit 'When to use' and 'When NOT to use' sections give clear context and exclusions, such as avoiding WHOIS/DNS lookups. It does not name alternative sibling tools, so it stops just short of the full 5-level guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Extract structured JSON data matching a custom schema directly from any webpage. Extracts clean content and processes schema mapping via fast LLM parsing. Requires x402 micropayment (0.015 USDC on Base).
When to use: Scraping structured data (product specs, prices, jobs, articles) into clean JSON. When NOT to use: Do NOT use for general open-ended chat without a defined schema.
Parameters:
url (string, required): Target webpage URL.
schema (object, required): JSON object describing fields or schema to extract.
instructions (string, optional): Specific guidance for extraction.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Target webpage URL. | |
| schema | Yes | Schema definition or list of fields to extract. | |
| instructions | No | Optional instructions for parsing or field formatting. |
| Name | Required | Description |
|---|---|---|
| url | Yes | |
| data | Yes | Extracted JSON fields |
| title | No | |
| elapsed_ms | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds critical behavioral context beyond annotations: the x402 micropayment requirement (0.015 USDC on Base) and the use of fast LLM parsing for schema mapping. It omits rate limits and failure modes, but those are not essential given the annotations and output schema.
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 front-loaded with the core action and the key payment constraint, then organized with use-case and parameter sections. It is efficient, though the opening sentence and the second sentence ('Extracts clean content...') are slightly redundant, and the parameter descriptions mostly duplicate the input schema.
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 full input schema, annotations, and output schema, the description covers the essential operational constraints: purpose, payment, and when not to use it. It would be more complete with explicit notes about limitations on 'any webpage' (e.g., dynamic rendering, auth walls) and clearer differentiation from sibling scraping tools.
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 structured schema already documents all parameters. The description's parameter list mostly restates the schema — url, schema, and optional instructions — without adding meaningful new semantics such as examples, formats, or edge-case behavior.
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 opens with a specific verb and resource: 'Extract structured JSON data matching a custom schema directly from any webpage.' This distinguishes it from siblings like read_web_page or search_web because it emphasizes schema-driven structured extraction, not just fetching or searching.
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?
It provides explicit 'When to use' and 'When NOT to use' guidance, including the exclusion of open-ended chat without a defined schema. However, it does not name alternative sibling tools or explain when to prefer read_web_page or fetch_stealth_web, so it stops short of full alternative routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch webpage HTML with modern browser TLS and header impersonation (Sec-Ch-Ua, realistic headers) to bypass bot protection and detect anti-bot challenges. Requires x402 micropayment (0.01 USDC on Base).
When to use: Fetching websites that block standard cURL or basic HTTP libraries with 403 Forbidden. When NOT to use: Do NOT use for downloading giant binary files (videos, zip archives).
Parameters:
url (string, required): Target webpage URL.
custom_headers (object, optional): Additional HTTP headers to pass along.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Target webpage URL. | |
| custom_headers | No | Optional custom headers. |
| Name | Required | Description |
|---|---|---|
| url | Yes | |
| html | Yes | |
| title | No | |
| elapsed_ms | No | |
| http_status | Yes | |
| challenge_type | No | |
| content_length | No | |
| challenge_detected | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the operation read-only and idempotent, and the description adds material behavior beyond that: it discloses a real cost (x402 micropayment, 0.01 USDC on Base), the impersonation technique, and the feature of detecting anti-bot challenges. No annotation contradiction exists.
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 front-loaded with the core purpose, then gives the cost and usage guardrails, then lists parameters. Every sentence carries useful information, and the parameter list is a compact summary rather than prose padding.
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 two-parameter tool with a full input schema, output schema, and safety annotations, the description covers purpose, cost, selection criteria, and exclusions. The only minor omission is the payment mechanism, but the cost and requirement are clearly stated and not needed to form the call.
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 the schema already documents both parameters. The description mostly restates the schema ('url' as target webpage, 'custom_headers' as additional headers) without adding format, precedence, or interaction semantics, which keeps it at the 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 names a specific verb and resource (fetch webpage HTML) and adds a distinctive purpose: bypassing bot protection via browser TLS/header impersonation, which separates it from generic readers like read_web_page and extractors like extract_json_from_web. The 'When to use' mention of 403s further clarifies the intended niche.
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?
It gives explicit when-to-use (sites returning 403 to standard clients) and when-not-to-use (downloading large binaries). It does not name sibling tools as alternatives, so it stops just short of the top anchor.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve current x402 pricing per 1,000 CAPTCHA solves across all supported types (Turnstile, hCaptcha, reCAPTCHA v2, Arkose, Cloudflare). Free endpoint with zero parameters.
When to use: Check current rates and atomic USDC requirements before calling solve_captcha. When NOT to use: Do NOT use to submit or solve CAPTCHA challenges.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| network | Yes | Target blockchain network (Base) |
| pricing | Yes | Map of CAPTCHA type to cost in USDC atomic units per 1,000 solves |
| currency | Yes | Payment currency (USDC) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish read-only, idempotent, non-destructive behavior, so the description only needs to add context beyond that. It adds that the endpoint is free, has zero parameters, and returns current pricing, which is useful operational context not present in annotations. The existence of an output schema covers the return-shape burden, so the lack of return-format detail is not a gap.
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 compact and front-loaded: the core purpose comes first, followed by two labeled usage directives. Every sentence adds information and none repeat schema or annotation content.
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 zero-parameter, read-only endpoint with an output schema and clear sibling context, the description covers purpose, scope, supported types, and usage boundaries. Nothing an agent needs to decide to call this tool is missing.
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 zero parameters and 100% schema coverage, there is nothing semantic to document. The description reinforces this by explicitly stating 'zero parameters,' so an agent knows no hidden inputs are expected.
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 opens with a specific verb—'Retrieve'—and a precise resource: current x402 pricing per 1,000 CAPTCHA solves, enumerating supported types. It is immediately distinguishable from siblings like solve_captcha because it frames the tool as an information endpoint, not a solving 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?
It explicitly states when to use the tool ('Check current rates and atomic USDC requirements before calling solve_captcha') and when not to ('Do NOT use to submit or solve CAPTCHA challenges'). It names the relevant sibling solve_captcha, giving an agent clear routing logic.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Extract clean, readable Markdown and metadata from any public webpage for LLM ingestion, stripping ads, popups, and navigational clutter. Returns clean markdown, title, description, character count, and estimated tokens. Requires x402 micropayment (0.005 USDC on Base).
When to use: Ingesting articles, blog posts, documentation, or news pages into LLM context. When NOT to use: Do NOT use for raw binary files (PDF/images), authenticated pages behind a login, or single-page apps that require heavy JavaScript rendering.
Parameters:
url (string, required): Full target webpage URL (e.g. 'https://news.ycombinator.com').
include_links (boolean, optional, default true): Whether to preserve markdown hyperlinks.
include_images (boolean, optional, default false): Whether to preserve image markdown links.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Full target webpage URL to extract markdown from. | |
| include_links | No | Preserve markdown hyperlinks. | |
| include_images | No | Preserve markdown image tags. |
| Name | Required | Description |
|---|---|---|
| url | Yes | Target webpage URL |
| title | No | Extracted page title |
| length | Yes | Content length in characters |
| content | Yes | Clean extracted Markdown content |
| elapsed_ms | No | Extraction time in milliseconds |
| description | No | Extracted meta description |
| estimated_tokens | No | Estimated LLM tokens (~len/4) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly and idempotent, but the description adds significant behavioral detail: it strips ads/popups/navigation, returns specific fields (markdown, title, description, character count, estimated tokens), and reveals a critical x402 micropayment requirement. This goes well beyond what annotations and schema provide.
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-organized with front-loaded purpose, return info, and payment notice, followed by clear usage guidance. The parameter bullet list is somewhat redundant with the schema, which prevents a perfect score, but overall it remains efficient and scannable.
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 read-only, three-parameter tool with an output schema, the description covers the essential context: behavior, return content, payment cost, use cases, and exclusions. There are no critical gaps that would prevent an agent from calling 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?
Input schema coverage is 100%, so the schema fully documents all three parameters. The description's parameter list largely repeats schema descriptions and adds no new meaning, such as URL format constraints or interaction between include_links and include_images.
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 names a specific verb and resource: extract clean Markdown and metadata from public webpages, with a clear intended use of LLM ingestion. It clearly conveys the tool's scope but does not explicitly name or differentiate sibling tools such as fetch_stealth_web or extract_json_from_web.
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 'When to use' and 'When NOT to use' guidance, covering article/blog ingestion and excluding binary files, authenticated pages, and JS-heavy SPAs. It lacks named alternatives, so it doesn't fully route the agent to a specific sibling tool, but the context is clear enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Execute live web searches using multi-engine chain (TinyFish, DuckDuckGo, Jina) without monthly API subscriptions. Returns fresh source URLs, titles, and snippets. Requires x402 micropayment (0.005 USDC on Base).
When to use: Real-time web browsing and information retrieval for AI agents. When NOT to use: Do NOT use for deep recursive crawling of entire sites.
Parameters:
query (string, required): Search query (3-300 chars).
limit (integer, optional, default 5): Maximum number of search results to return (1-10).
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Number of results to return. | |
| query | Yes | Web search query. |
| Name | Required | Description |
|---|---|---|
| count | No | Number of returned results |
| query | Yes | Original search query |
| results | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations (readOnlyHint, idempotentHint, destructiveHint=false), the description discloses the multi-engine chain, the required x402 micropayment and cost, and the return shape of 'fresh source URLs, titles, and snippets.' This adds meaningful operational context an agent needs before invoking the tool.
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 and front-loaded: it states the core action, adds key constraints, then gives usage guidance and parameter details. Every sentence earns its place, with no filler or tautology.
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 tool with only two parameters, an output schema, and clear annotations, the description provides all essential context: what it does, what it returns, when to use it, when not to use it, and the required micropayment. Nothing material is missing for an agent to select and invoke 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?
The schema already documents both parameters with descriptions, defaults, and constraints, so coverage is 100%. The description repeats the same parameter details (e.g., query 3-300 chars, limit 1-10) without adding new semantic meaning or usage advice beyond what the input 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 the tool's function with a specific verb ('Execute live web searches') and resource ('web'), and details what it returns ('fresh source URLs, titles, and snippets'). This distinguishes it from siblings like read_web_page or fetch_stealth_web, which do different tasks. The explicit 'When NOT to use' also sharpens the boundary.
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 'When to use' and 'When NOT to use' guidance, including a concrete exclusion ('deep recursive crawling of entire sites'). However, it does not name an alternative tool for that excluded case or compare itself to siblings, so it stops short of full routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Solve web CAPTCHA challenges (Turnstile, hCaptcha, reCAPTCHA v2, Arkose, Cloudflare) and return a valid solution token. Automatically retries once on failure without double charging. Requires x402 payment on Base.
When to use: Use when an agent encounters a bot wall or CAPTCHA challenge during automated web workflows. When NOT to use: Do NOT use for non-CAPTCHA auth, 2FA/OTP codes, or general login forms.
Parameters:
type (string, required): CAPTCHA type ('turnstile', 'hcaptcha', 'recaptcha', 'arkose', 'cloudflare').
sitekey (string, required): Public sitekey extracted from the target page DOM.
url (string, required): Full target webpage URL hosting the challenge.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The full target page URL where the CAPTCHA challenge is hosted. | |
| type | Yes | The specific type of CAPTCHA challenge encountered on the target page. | |
| sitekey | Yes | The CAPTCHA sitekey parameter extracted from the target page DOM or iframe. |
| Name | Required | Description |
|---|---|---|
| token | Yes | The resulting CAPTCHA response token to submit to the form |
| method | No | Solving method or backend engine used |
| solved | Yes | Whether the CAPTCHA challenge was successfully solved |
| elapsed | No | Time taken in seconds to solve the challenge |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Given all-false annotations (readOnlyHint, idempotentHint, destructiveHint), the description carries the full behavioral burden and delivers: 'Automatically retries once on failure without double charging' and 'Requires x402 payment on Base' disclose retry, billing, and payment/auth semantics that the structured annotations cannot express.
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 front-loads the core purpose, followed by a compact retry/billing note and clearly labeled When to use/When NOT to use sections. The redundant inline Parameters section duplicates schema coverage that is already 100%, adding length without new value, which prevents a 5.
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?
With an output schema present and the parameter schema fully documented, the description need not explain return values. It covers purpose, usage boundaries, payment, and retry behavior. Minor gaps remain: 'failure' for the retry condition is undefined, and 'reCAPTCHA v2' doesn't exactly match the enum value 'recaptcha'.
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% (all three params have descriptions, examples, and an enum for type), so the baseline is 3. The inline Parameters section merely restates the schema — in one spot less precisely ('sitekey extracted from the target page DOM' vs the schema's 'DOM or iframe') — without adding new meaning.
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 opens with a specific verb and resource: 'Solve web CAPTCHA challenges (Turnstile, hCaptcha, reCAPTCHA v2, Arkose, Cloudflare) and return a valid solution token.' It enumerates concrete CAPTCHA types and the 'When NOT to use' boundary distinguishes it from auth-related siblings, making tool selection 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?
Explicit 'When to use' and 'When NOT to use' sections state that the tool is for bot walls/CAPTCHA challenges and rule out non-CAPTCHA auth, 2FA/OTP, and general login forms. It stops short of naming a specific alternative sibling tool (e.g., get_captcha_pricing) for those excluded cases, which keeps it from a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Verify whether an AI model, API provider, pricing claim, or infrastructure assertion is true today using live web evidence. Returns deterministic verdicts (TRUE, FALSE, PARTIALLY_TRUE, UNREACHABLE, UNVERIFIED) with cited sources and confidence scores. Requires x402 micropayment (0.01 USDC on Base).
When to use: Fact-checking an AI provider's claims, pricing, or model availability. When NOT to use: Do NOT use for general open-ended web search, coding assistance, or non-AI claim verification.
Parameters:
query (string, required): The exact claim or assertion to verify (5-500 chars), e.g. 'Is GLM-5.3 Flash free on ZenMux?'.
depth (string, optional, default 'standard'): Verification depth. 'standard' executes fast single-pass search (0.01 USDC); 'deep' conducts multi-source cross-examination (0.03 USDC).
| Name | Required | Description | Default |
|---|---|---|---|
| depth | No | Verification depth: 'standard' (0.01 USDC) or 'deep' (0.03 USDC). | standard |
| query | Yes | The specific AI infrastructure claim or assertion to verify. |
| Name | Required | Description |
|---|---|---|
| id | No | Unique verification record ID |
| answer | Yes | Detailed explanation backed by fresh sources |
| sources | Yes | Fresh evidence sources used for verification |
| verdict | Yes | Deterministic evidence-backed verdict |
| confidence | Yes | Confidence score between 0.0 and 1.0 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds meaningful behavioral context beyond those: it requires an x402 micropayment, returns validated verdicts with cited sources and confidence scores, and distinguishes standard vs deep verification costs. No contradiction with annotations exists.
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 a clear purpose statement, explicit usage guidance, and a parameter breakdown. It is not overly verbose, though the parameter section partially duplicates the input schema. The most important differentiators, cost and when-not-to-use, are prominently placed.
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, two parameters, and presence of an output schema, the description covers all essential context: purpose, scope, exclusions, cost, verdict types, and parameter depth behavior. The output schema handles return-value details, so no critical information is missing.
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 some value by explaining depth behavior as 'fast single-pass search' vs 'multi-source cross-examination' and explicitly tying costs to each depth level. The query parameter guidance is useful but largely mirrors the schema's existing description.
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 verb and resource: 'Verify whether an AI model, API provider, pricing claim, or infrastructure assertion is true today using live web evidence.' It also lists deterministic verdicts and clearly separates this tool from general web search, making it distinguishable from siblings like search_web.
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 provides 'When to use' and 'When NOT to use' guidance, including exclusions for general open-ended web search, coding assistance, and non-AI claims. It stops short of naming a specific sibling tool to use instead, such as search_web, so it is clear but not fully alternative-aware.
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.
check_endpoint_health1 field changedInput schema / additionalPropertiesAdded value: +falseextract_json_from_web1 field changedInput schema / additionalPropertiesAdded value: +falsefetch_stealth_web1 field changedInput schema / additionalPropertiesAdded value: +falseget_captcha_pricing1 field changedInput schema / additionalPropertiesAdded value: +falseread_web_page1 field changedInput schema / additionalPropertiesAdded value: +falsesearch_web1 field changedInput schema / additionalPropertiesAdded value: +falsesolve_captcha1 field changedInput schema / additionalPropertiesAdded value: +falseverify_ai_claim1 field changedInput schema / additionalPropertiesAdded value: +falseextract_json_from_webfetch_stealth_websearch_webread_web_pagecheck_endpoint_health4 fields changedInput schema / properties / url / descriptionPrevious value: -"The target API or service endpoint URL to probe (e.g., 'https://api.example.com/v1/chat')."New value: +"The target API or service endpoint URL to probe."Input schema / properties / url / examplesAdded value: +[
+ "https://openrouter.ai/api/v1/models",
+ "https://api.together.xyz/v1/health"
+]Input schema / properties / url / maxLengthAdded value: +1000Input schema / properties / url / minLengthAdded value: +8solve_captcha8 fields changedInput schema / properties / sitekey / examplesAdded value: +[
+ "0x4AAAAAAAx..."
+]Input schema / properties / sitekey / maxLengthAdded value: +256Input schema / properties / sitekey / minLengthAdded value: +5Input schema / properties / type / examplesAdded value: +[
+ "turnstile",
+ "recaptcha",
+ "hcaptcha"
+]Input schema / properties / url / examplesAdded value: +[
+ "https://example.com/login"
+]Input schema / properties / url / formatAdded value: +"uri"Input schema / properties / url / maxLengthAdded value: +1000Input schema / properties / url / minLengthAdded value: +8verify_ai_claim5 fields changedInput schema / properties / depth / examplesAdded value: +[
+ "standard",
+ "deep"
+]Input schema / properties / query / descriptionPrevious value: -"The specific AI infrastructure claim or assertion to verify (e.g., 'Is GLM-5.3 Flash free on ZenMux?')."New value: +"The specific AI infrastructure claim or assertion to verify."Input schema / properties / query / examplesAdded value: +[
+ "Is GLM-5.3 Flash free on ZenMux?",
+ "Does OpenRouter still offer free tier models?"
+]Input schema / properties / query / maxLengthAdded value: +500Input schema / properties / query / minLengthAdded value: +5check_endpoint_healthget_captcha_pricingverify_ai_claim1 field changedInput schema / properties / depth / defaultAdded value: +"standard"solve_captcha5 fields changedInput schema / properties / sitekey / descriptionAdded value: +"The CAPTCHA sitekey parameter extracted from the target page DOM or iframe."Input schema / properties / type / descriptionAdded value: +"The specific type of CAPTCHA challenge encountered on the target page."Input schema / properties / type / enumAdded value: +[
+ "turnstile",
+ "hcaptcha",
+ "recaptcha",
+ "arkose",
+ "cloudflare"
+]Input schema / properties / url / descriptionAdded value: +"The full target page URL where the CAPTCHA challenge is hosted."Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "elapsed": {
+ "description": "Time taken in seconds to solve the challenge",
+ "type": "number"
+ },
+ "method": {
+ "description": "Solving method or backend engine used",
+ "type": "string"
+ },
+ "solved": {
+ "description": "Whether the CAPTCHA challenge was successfully solved",
+ "type": "boolean"
+ },
+ "token": {
+ "description": "The resulting CAPTCHA response token to submit to the form",
+ "type": "string"
+ }
+ },
+ "required": [
+ "solved",
+ "token"
+ ],
+ "type": "object"
+}verify_ai_claim3 fields changedInput schema / properties / depthAdded value: +{
+ "description": "Verification depth: 'standard' (0.01 USDC) or 'deep' (0.03 USDC).",
+ "enum": [
+ "standard",
+ "deep"
+ ],
+ "type": "string"
+}Input schema / properties / query / descriptionAdded value: +"The specific AI infrastructure claim or assertion to verify (e.g., 'Is GLM-5.3 Flash free on ZenMux?')."Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "answer": {
+ "description": "Detailed explanation backed by fresh sources",
+ "type": "string"
+ },
+ "confidence": {
+ "description": "Confidence score between 0.0 and 1.0",
+ "type": "number"
+ },
+ "id": {
+ "description": "Unique verification record ID",
+ "type": "string"
+ },
+ "sources": {
+ "description": "Fresh evidence sources used for verification",
+ "items": {
+ "properties": {
+ "title": {
+ "description": "Source page title",
+ "type": "string"
+ },
+ "type": {
+ "description": "Source type (official, third_party, community)",
+ "type": "string"
+ },
+ "url": {
+ "description": "Source URL",
+ "type": "string"
+ }
+ },
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "verdict": {
+ "description": "Deterministic evidence-backed verdict",
+ "enum": [
+ "TRUE",
+ "FALSE",
+ "PARTIALLY_TRUE",
+ "CHANGED",
+ "UNREACHABLE",
+ "BLOCKED",
+ "UNVERIFIED"
+ ],
+ "type": "string"
+ }
+ },
+ "required": [
+ "verdict",
+ "answer",
+ "confidence",
+ "sources"
+ ],
+ "type": "object"
+}solve_captchaverify_ai_claim
Add one secure layer between your agents and this server.