Check how to contact a business website, and whether that contact path actually works.
Scored across 1 tool
With only one tool, there is no possibility of confusion or overlap between tools. The single tool's purpose is clearly defined and distinct by default.
The lone tool name 'check_contact_path' is descriptive and follows a clear verb_noun pattern. While consistency cannot be fully assessed with one tool, the name itself is well-formed and predictable.
A single tool is too few for a server advertising business contact finding. The tool covers only one specific action, leaving the server feeling thin and incomplete for its stated domain.
The domain implies finding contact information for businesses, but only one path-checking tool exists. There are no tools for searching businesses, resolving domains, or retrieving contact details independently, creating significant gaps.
Given a business website URL, report how a human is meant to make contact and whether that path is actually reachable. Returns a verdict of 'reachable' or 'inconclusive', the forms found with their resolved handler URLs, and any published phone or email. Never submits anything. Answers 'inconclusive' rather than guessing when a site is client-rendered, bot-protected or parked -- about 64% of real sites cannot be judged from outside, and a confident wrong answer is worse than an honest one.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The business website URL, e.g. https://example.com |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it succeeds: 'Never submits anything' is a critical safety disclosure, while the explanation of 'inconclusive' on client-rendered/bot-protected/parked sites and the 'about 64%' figure transparently set expectations about reliability. The rationale that a confident wrong answer is worse than an honest one further clarifies decision-making behavior.
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 main purpose, then covers return values, safety, and limitations in logical order. Every sentence earns its place: the 64% statistic and the honest-vs-confident rationale directly support the 'inconclusive' behavior, and nothing is redundant or 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?
There is no output schema, so the description must define the return contract; it does so explicitly by naming the verdict values and the data included (forms with resolved handler URLs, phone, email). It also covers edge-case behavior and the interpretation of inconclusive results, making it complete for an agent to invoke the tool correctly and understand 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?
The single parameter is already fully documented by the schema (description, required, pattern, patternMessage), so schema coverage is 100%. The description's phrase 'business website URL' mirrors the schema without adding new semantics. It provides no format, syntax, or additional meaning beyond what the schema already conveys, so the 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?
States a specific verb and resource: 'report how a human is meant to make contact and whether that path is actually reachable' for a 'business website URL'. It also explicitly enumerates the return components (verdict, forms, handler URLs, phone/email), leaving no ambiguity about what the tool does. With no sibling tools, differentiation is unnecessary, but the self-contained clarity is excellent.
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?
There is no explicit 'use this when' statement, but the description's opening clause makes the use case self-evident: given a business website URL, assess contact reachability. It does not name alternatives (there are none) and includes no exclusions, but it does describe the conditions under which the tool will be inconclusive, which guides expectation-setting about when the tool is useful.
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_contact_pathCheck how to contact a business website, and whether that contact path actually works.
Is this business's website still there? Checks apex and www, and DNS separately from HTTP.
Scan a business website and see if AI agents can find it, trust it, and act on it.
Check how well AI agents can discover and understand a public website.
Add one secure layer between your agents and this server.
