Checks whether a web page is ready for AI agents and whether an MCP server meets directory rules
Scored across 2 tools
The two tools target clearly different objects (an MCP server endpoint vs. a general webpage) and each description explicitly redirects to the sibling tool for the other case. There is no realistic way an agent would confuse directory-compliance checking with AI-readiness scanning.
Both names follow a consistent snake_case verb_object_qualifier pattern (check_mcp_server_directory_rules, scan_webpage_ai_readiness). The verbs differ (check vs. scan) but each accurately describes its action, so the convention reads predictably.
Two tools is on the thin side for a standalone server, and each is a fairly heavy single-purpose scan. The scope is tight and each tool earns its place, but the surface feels minimal rather than well-rounded.
The two complementary scans cover the stated domain of AI-readiness/compliance assessment, and both return scores, checks, and fixes. The only gap is that detailed results live behind a reportUrl with no companion tool to fetch or list reports.
Returns server details, tool counts, directory-specific results, individual checks, and a full report link after connecting to a public remote MCP server and reading its tool list without calling tools. Use it when someone asks whether an MCP server meets ChatGPT or Claude directory requirements; for scanning a regular webpage's AI readiness, use scan_webpage_ai_readiness instead. Pass url as the public MCP server address to check its connection, sign-in, domain, and tool rules.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Address of the public remote MCP server to check, such as https://mcp.example.com/mcp. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely new behavior: it connects to the remote server and reads its tool list *without calling tools*, and it enumerates the checks performed (connection, sign-in, domain, tool rules). It stops short of noting failure modes such as unreachable or auth-gated servers, which keeps it below a 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?
Three tight sentences with no filler; the return-value inventory and the sibling contrast are both front-loaded. The opening return list is somewhat dense but each item is informative.
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 compensates by enumerating the return shape (server details, tool counts, directory results, individual checks, report link) and the side-effect boundary (reads tool list, does not call tools). Nothing critical for correct invocation 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% and the single url parameter is fully documented with an example, so the schema does the heavy lifting. The description only reinforces the 'public MCP server address' constraint, which is already implied by the schema, so a 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 gives a specific verb and resource — checking whether a public remote MCP server passes ChatGPT/Claude directory rules — and immediately distinguishes it from the one sibling, scan_webpage_ai_readiness. An agent can route correctly without opening any schema.
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 states the triggering condition ('when someone asks whether an MCP server meets ChatGPT or Claude directory requirements') and names the alternative tool plus the condition that selects it ('for scanning a regular webpage's AI readiness'). Both the use case and the exclusion are explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Returns a readiness score, passed and failed checks, category results, top fixes, limitations, and a report link for one public webpage. Use it when someone asks whether a webpage is accessible and usable by AI agents; for checking an MCP server's directory compliance, use check_mcp_server_directory_rules instead. Pass url to scan the page directly, or use the reportUrl to revisit the detailed results.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Public webpage address to scan, such as https://example.com or example.com/pricing. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, open-world, idempotent, and non-destructive behavior, yet the description adds what the result contains (score, passed/failed checks, category results, top fixes, limitations, report link) and how reportUrl lets you revisit results. It does not mention any rate limits or access requirements for the scan, leaving a small 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?
Front-loaded with the return value and the purpose, then the sibling routing, then the parameter usage. Three tight sentences with no filler.
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, and the description compensates by enumerating the returned fields, so an agent knows what to expect. A one-parameter read-only tool needs nothing more.
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% for the single url parameter, so baseline is 3. The description adds that the page must be public and clarifies the url-versus-reportUrl relationship, though reportUrl appears to be an output field rather than a parameter, which is slightly ambiguous.
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 and resource (scan a webpage for AI readiness) and enumerates what the scan yields. It also explicitly names the sibling tool it is not, so an agent can route without opening either schema.
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 an explicit trigger ('when someone asks whether a webpage is accessible and usable by AI agents') and an explicit alternative ('for checking an MCP server's directory compliance, use check_mcp_server_directory_rules instead').
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_mcp_server_directory_rulesscan_webpage_ai_readinessCheck whether a website is ready for AI agents (UCP, WebMCP, Access) and monitor your own sites.
Check if a website is down, explain browser errors and score agent readability (MCP, WebMCP).
Check if a website will block your AI agent and find its llms.txt, MCP or OpenAPI door.
Network, domain and website diagnostics for AI clients via MCP.
Add one secure layer between your agents and this server.