Checks a public web page in a real browser for analytics and ad conversion tags. No key needed.
Scored across 1 tool
There is only one tool, so there is no possibility of misselection between overlapping tools. Its purpose — verifying analytics/ad tag presence on a single public page — is stated unambiguously in the description.
The single name 'check_site_tracking' follows a clear verb_noun snake_case convention that directly describes the action and resource. Nothing in the naming is vague or mismatched.
A one-tool surface is thin even for a narrow purpose; there is no companion operation to batch, retrieve cached results, or enumerate supported tags. The single tool is substantial rather than trivial, so this is borderline rather than a severe mismatch.
The core check is covered, but the lifecycle is a dead end: agents cannot re-fetch cached results, check multiple pages/domains in one call, or query which tags the service can detect. The consent-gated caveat is disclosed but left entirely to the caller to work around.
Loads one public web page in a real browser and reports which analytics and ad conversion tags were seen, which were not, and which could not be verified. Use when someone asks whether a business website's tracking is set up. Takes up to about a minute. Results are cached for 24 hours per domain. A server-side or consent-gated setup can be invisible to this check and still work.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The website to check, such as example.com |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/openWorld/idempotent/non-destructive, and the description goes well beyond them: roughly one-minute latency, 24-hour per-domain result caching, and a stated blind spot for server-side or consent-gated tracking. Those three facts directly affect whether an agent should re-run the tool or how it should phrase results.
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?
Five short sentences, front-loaded with what it does, then when to use it, then latency, caching, and the caveat. No sentence is filler; each one changes how an agent would call or report on the tool.
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 one-parameter, no-output-schema tool, the description covers cost (time), freshness (cache), and interpretation risk (invisible setups) — the three things an agent needs to call it responsibly and describe results accurately.
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% with a single documented `url` parameter, so the schema carries parameter semantics. The description adds only the implicit constraint that the target must be a public page, which is useful but marginal — baseline 3 applies.
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?
Opens with a specific verb+resource pair: loads one public web page in a real browser and reports analytics/ad conversion tag status. The three-way outcome split (seen / not seen / unverifiable) tells an agent exactly what kind of answer to expect.
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?
"Use when someone asks whether a business website's tracking is set up" gives a concrete trigger, and the false-negative caveat about server-side or consent-gated setups sets an important boundary on interpretation. No sibling tools exist to route to, so the missing alternative-naming does not cost much.
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_site_trackingCheck one web page for broken links, redirect chains hop by hop and mixed content. Free, no key.
Checks a public website in six areas and returns scores from 0 to 100. Free, no key needed.
Check a page, AI-crawler access, llms.txt and backlinks of a site. Free, read-only.
Indexability, robots.txt, sitemap, TLS, domain expiry and Googlebot-vs-browser checks. No account.
Add one secure layer between your agents and this server.