Skip to main content
Glama

Website prüfen

check_site
Read-only

Zwei Teile. SYSTEM: läuft die Website überhaupt – Adresse auf der richtigen Domain, DNS-Eintrag, wird ausgeliefert, Badge passend zum Plan. Das ist die Antwort auf «meine Seite ist nicht da» oder «das Badge ist noch da», und sie gehört nicht in die Dateien: dafür gibt es im Portal einen Knopf. SITE: Auffindbarkeit (Titel, Beschreibung, sitemap), Teilen (Open Graph), Technik (kaputte Verweise, fehlende Dateien), Tempo (Gewicht, blockierende Skripte), Zugänglichkeit (alt-Texte, Bildmasse), Inhalt und Lesbarkeit für Sprachmodelle, Datenschutz (fremde Server). Vor jedem publish aufrufen, und immer dann, wenn jemand sagt, mit der Seite stimme etwas nicht.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "website": "<website>"
    },
    "name": "check_site"
  }
}

Input Schema

NameRequiredDescriptionDefault
stufeNoAb welcher Stufe melden. Vorgabe: alles.
websiteYesKennung oder Name der Website. Reicht der Zugang ueber mehrere Organisationen und gibt es die Kennung mehrfach, «organisation/website» schreiben.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, so no credit is needed for safety; the description instead adds real behavioral content by enumerating the seven audit dimensions actually inspected, which the agent cannot infer elsewhere. It omits result format and any note on runtime cost of a full audit. Minor tension: openWorldHint=false while the description mentions DNS records and "fremde Server" checks, though these plausibly stay within the platform's own site scope rather than arbitrary external entities.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with "Zwei Teile." and then two clearly labeled blocks, so a reader can stop after SYSTEM if that is all they need. The SITE checklist is a long enumeration, but each item is a distinct check rather than padding; slightly tighter grouping would earn a 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the definition carries the burden of telling the agent what the tool looks at, and it does so comprehensively via the SYSTEM/SITE taxonomy plus the severity filter implied by `stufe`. What is missing is how findings are returned (list? per-category report? pass/fail counts), which matters for a reporting tool of this breadth.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so both `website` (identifier vs. `organisation/website` form) and the `stufe` severity enum are already documented in the schema. The description adds no further semantics about the severity threshold or the identifier format, leaving parameter meaning entirely to structured fields — the baseline 3 case.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names the specific resource (Website) and splits the job into two explicitly labeled parts, SYSTEM (reachability, DNS, delivery, plan badge) and SITE (SEO, Open Graph, broken links, speed, accessibility, LLM readability, privacy). It also positively distinguishes itself from the file tools ("sie gehört nicht in die Dateien: dafür gibt es im Portal einen Knopf"), so an agent can separate it from fs_* and publish siblings 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.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives two explicit triggers: "Vor jedem publish aufrufen" and "immer dann, wenn jemand sagt, mit der Seite stimme etwas nicht", plus the concrete user phrasings it answers ("meine Seite ist nicht da", "das Badge ist noch da"). It additionally states a when-NOT: file-level checks belong elsewhere, which is rare and valuable routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources