Score any website's AI search visibility out of 100 and see which of 20 AI crawlers can read it.
Scored across 2 tools
check_ai_crawlers is effectively a subset of check_ai_visibility, which explicitly includes 'AI crawler access' as one of its five scored groups. The descriptions do differentiate scope (detailed per-bot diagnosis vs. overall 100-point score), but an agent asked 'can AI read my site?' could reasonably land on either tool. The overlap is real and only partly resolved by the text.
Both tools follow the identical verb_noun pattern with a shared check_ai_ prefix and snake_case throughout. With only two names, the convention is perfectly predictable.
Two tools is thin even for a narrowly scoped audit service, and one of them is largely subsumed by the other. A drill-down plus an aggregate is a defensible pairing, but the set feels minimal rather than deliberately scoped.
Together the tools cover crawler access, machine-readability, structured data, entity/authority and AI-ready content, with per-problem point attribution — a solid diagnostic surface. Gaps remain: no way to audit a non-homepage URL, no remediation or re-check/history operation, and no comparison between sites.
Shows which of 20 AI crawlers can read a website's homepage: AI search and answer bots (OAI-SearchBot, ChatGPT-User, Claude-SearchBot, PerplexityBot, Googlebot, Bingbot and more) and AI training bots (GPTBot, ClaudeBot, Google-Extended, CCBot and more). Applies the site's robots.txt rules per bot the way RFC 9309 and Google do, tests the firewall by fetching the homepage as a browser and as four AI bots, and reports llms.txt and sitemap lines. Takes about 10 seconds.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | The website to check, as a domain such as example.com. A full URL also works; only the hostname is used. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotent, non-destructive and open-world behavior, and the description still adds substantial context: it applies robots.txt rules per RFC 9309 and Google's interpretation, fetches the homepage as a browser and four AI bots to test firewalls, reports llms.txt and sitemap lines, and discloses a ~10 second runtime. This is exactly the kind of method-and-cost disclosure that helps an agent plan the call.
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 core purpose is front-loaded in the first clause, with the bot enumeration parenthetically contained. The second sentence carries method, output, and timing without filler. The long first sentence is dense but every clause 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 single-parameter, non-destructive read tool with no output schema, the description supplies everything needed: scope (homepage), method (robots.txt semantics, dual fetching), outputs (crawler readability, firewall behavior, llms.txt, sitemap), and runtime. Nothing an agent needs in order to call it or interpret the result 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 coverage is 100%: the single `domain` parameter is fully documented in the schema, including that a full URL works and only the hostname is used. The description adds only the framing that the homepage is what gets checked, so it neither needs to nor does add parameter-level detail beyond the schema. 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 opens with a specific verb and resource ('Shows which of 20 AI crawlers can read a website's homepage') and even enumerates the bot categories covered. It is unambiguous about what the tool does, but it never mentions the sibling check_ai_visibility or explains how the two differ, which keeps it from a 5.
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?
Usage is only implied: an agent can infer this is the tool for checking crawler access to a site. There is no explicit guidance on when to choose this over check_ai_visibility, no prerequisites, and no exclusion conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Scores how well AI search engines (ChatGPT, Perplexity, Gemini, Google AI Overviews) can find, read and understand a website. Runs 30 checks in five groups: AI crawler access, what the homepage tells machines, structured data, entity and authority (Wikidata, Wikipedia, linked profiles) and AI-ready content (llms.txt, pricing, proof, docs, comparison pages). Returns a score out of 100, a grade, a score per group and every problem found, with the points it costs. Takes 10 to 30 seconds.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | The website to check, as a domain such as example.com. A full URL also works; only the hostname is used. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, openWorld), and the description adds genuinely useful context beyond them: the exact breadth (30 checks in five named groups), the latency ('takes 10 to 30 seconds'), and the shape of the result. That latency disclosure is exactly the kind of operational detail annotations cannot convey.
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?
Three sentences, front-loaded with what is scored, then the breakdown of checks, then what comes back and how long it takes. No filler, no repetition of the title, and the most decision-relevant facts (breadth, output, latency) lead.
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?
No output schema exists, yet the description fully characterizes the return value — score out of 100, grade, per-group scores, and every problem with its point cost — plus runtime. For a single-parameter read-only audit tool, an agent has everything needed to call it and interpret the result.
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% and there is only one required parameter, so the schema already explains the domain format and that a full URL is accepted with only the hostname used. The description adds no parameter-level detail, which matches the baseline 3 for schema-covered inputs.
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?
Specific verb and resource: 'Scores how well AI search engines ... can find, read and understand a website', naming the four engines and the five check groups. The scope is unmistakable, but it never names or contrasts with the sibling check_ai_crawlers, even though 'AI crawler access' is listed as one of its own groups — the agent must infer that relationship.
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?
Usage is implied: run this for a full AI-visibility audit of a site, since it bundles 30 checks across five areas. There is no explicit when-to-use vs. when-not-to-use, and no routing to check_ai_crawlers for a narrower crawler-only check, so the agent is left to infer which of the two tools to pick.
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_ai_crawlerscheck_ai_visibilityScan any website's AI readiness: AI search visibility and AI agent usability. Free, no auth.
Scan any public website and see how ready it is for AI agents and AI search, explained plainly.
Audit any site's AI visibility from your assistant: crawler access, rendering, and schema.
AEO audit: score any website 0-100 for AI visibility. Checks schema, meta, content, AI crawlers.
Add one secure layer between your agents and this server.