wake_check_siteProbe a public hostname the way an AI agent sees it (homepage, robots.txt, llms.txt, sitemap, agent card) and return scores out of 100 with concrete recommendations and publish-ready llms.txt / robots files. Input is a hostname only; the probe keeps structural signals, never page bodies. No account needed.
| Name | Required | Description | Default |
|---|---|---|---|
| host | No | Public hostname, e.g. docs.example.com |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds real context beyond the annotations: it discloses what is fetched, that only structural signals are retained ('never page bodies'), and that no account is required — privacy and auth facts the annotations do not convey. Minor tension: annotations set openWorldHint=false while probing arbitrary public hosts is arguably external, though this is a judgement call rather than a direct contradiction.
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?
Two sentences, both load-bearing: the first defines the probe and its outputs, the second covers input shape, data handling, and auth. Nothing is repeated and the core action comes first.
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 read-only tool with no output schema, the description covers what is inspected, what is returned, what is retained, and that no auth is needed. An agent has everything required to decide to call it and what to expect back.
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 already 100%, so baseline is 3, but 'Input is a hostname only' usefully reinforces that no scheme or path belongs in the value, which the schema's example alone leaves ambiguous. It does not add syntax or validation detail beyond that.
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?
Names a specific verb (probe) and resource (a public hostname), and enumerates exactly what gets inspected: homepage, robots.txt, llms.txt, sitemap, agent card. The stated output (scores out of 100, recommendations, publish-ready llms.txt/robots files) makes it unmistakably different from the only sibling, wake_about.
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?
The description scopes the call ('Input is a hostname only', 'No account needed') but never states when to reach for this tool versus an alternative or when it should not be used. With a single, unrelated sibling the risk of misrouting is low, but the guidance is implied rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.