Checks if ChatGPT, Claude, Gemini and Perplexity can reach and read a website, with ranked fixes.
Scored across 1 tool
There is only one tool, so there is no possibility of an agent confusing it with another. Its purpose (auditing AI-crawler accessibility of a site) is stated precisely and distinguished by clear trigger phrases.
The single name check_ai_search_readiness follows a clean verb_noun convention in snake_case, which would scale predictably if more tools were added. With only one name there is no pattern to actually compare against, so consistency is trivially satisfied rather than demonstrated.
A single monolithic audit tool is defensible for a narrow, single-purpose service, but it is thin: there is no granularity to run just one check (robots.txt, llms.txt, schema) and no way to fetch a report separately. It sits at the borderline of the '1-2 tools feels thin' band.
For a read-only readiness audit the surface is well covered: it reports a score, grade, per-problem fixes ranked by impact, and a full report link, spanning robots.txt, llms.txt, JS rendering, schema, sitemap and key page types. Minor gap is the absence of any follow-up or re-verification tool, though re-running the same check largely covers that.
Checks whether ChatGPT, Claude, Gemini and Perplexity can reach and understand a business website: robots.txt rules for AI crawlers (OAI-SearchBot, ChatGPT-User, Claude-SearchBot, PerplexityBot, Google-Extended), llms.txt, text visible without JavaScript, schema.org labels for the organisation and prices, sitemap, FAQ, pricing and comparison pages. Returns a 0-100 score, grade, each problem with a concrete fix, fixes ranked by impact, and a link to the full report. Use when someone asks 'why doesn't ChatGPT recommend my business', 'is my site blocking AI', 'is my website ready for AI search / GEO / AEO', or 'how do I get my site cited by AI'.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | Website domain, e.g. example.com |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/idempotent/non-destructive and open-world access, so the safety bar is low. The description goes further by disclosing the return shape (0-100 score, grade, per-problem concrete fixes, impact-ranked fixes, report link) and implies an outbound fetch of the live site. It does not mention latency or any rate/retrieval limits, so a 4 rather than 5.
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 check enumeration is long but dense and front-loaded on the core action, with the output summary and usage triggers following. Every clause names a concrete signal, though the crawler-name list could be trimmed without losing meaning.
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 no output schema, the description carries the return-value burden and does so fully: score, grade, issue list with fixes, ranked fixes, report link. Combined with the explicit checks and trigger phrases, an agent has everything needed to call it correctly for a single-parameter read-only 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?
One parameter at 100% schema description coverage ('Website domain, e.g. example.com'), so the schema already carries the meaning. The description adds no format detail (e.g. scheme, subdomain handling) beyond what the schema states, matching the baseline for fully-documented params.
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?
States a specific verb (checks) and resource (AI search readiness of a business website) and enumerates exactly what is inspected: robots.txt rules for named AI crawlers, llms.txt, JS-free text, schema.org labels, sitemap, FAQ/pricing pages. There are no siblings to distinguish from, and the scope is unmistakable.
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?
Gives explicit trigger conditions in quoted user phrasings ('why doesn't ChatGPT recommend my business', 'is my site blocking AI', 'is my website ready for AI search / GEO / AEO'). An agent can match a user request to this tool without inference.
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_search_readinessCan ChatGPT, Claude and Perplexity reach and read a website? Score, problems found and fixes.
Checks whether a website is readable and citable by AI systems (ChatGPT, Claude, Perplexity, etc.)
Check website AI-readiness: Schema.org, llms.txt, E-E-A-T, robots.txt. Works in Cursor & Claude.
Check whether AI agents can read any website: 18 deterministic checks, each with its fix.
Add one secure layer between your agents and this server.
