Skip to main content
Glama

Lepiej Widoczny – audyt WordPress/WooCommerce

Pełny audyt strony WordPress/WooCommerce (LW Audit)

audyt_strony
Read-onlyIdempotent

Pełny audyt strony lub sklepu według standardu LW Audit: 68 testów w 8 kategoriach (szybkość, Google i asystenci AI, udostępnianie linków, telefon i dostępność, katalog WooCommerce, higiena techniczna, zgodność z prawem i wymaganiami operatorów płatności – Przelewy24, PayU, Paynow, Autopay, Stripe – oraz gotowość na zakupy przez asystentów AI: dostęp botów zakupowych, GTIN/marka, dostawa i zwroty w danych, oceny). Zwraca oceny 0–100, wyniki testów z wartościami i dowodami, porównanie z 307 polskimi sklepami WooCommerce, plan poprawy (zrób sam / usługa z ceną) i dane katalogu produktów. Trwa 5–20 s, wynik w pamięci 12 h.

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": {
      "url": "<url>"
    },
    "name": "audyt_strony"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesAdres strony lub sklepu, np. twoj-sklep.pl

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already establish read-only, idempotent, non-destructive, open-world behavior, and the description adds genuinely new operational context: 5–20 s runtime and a 12 h in-memory result cache, which tells the agent to expect latency and that repeats may be served from cache. It also enumerates what the response contains (0–100 scores, test evidence, benchmark against 307 stores, remediation plan with prices, product catalog data). It does not state failure modes (non-WordPress URL, unreachable site) or whether the site must be publicly accessible, which keeps it below 5.

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?

Purpose and test scope are front-loaded, and the tail packs output contract, duration and cache TTL into one dense block with no filler. The long parenthetical enumerating payment operators and AI-readiness sub-checks is heavy but each element is informative rather than redundant.

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 description correctly carries the burden of describing return values, and it does so thoroughly, plus timing and caching. What remains unstated is failure/precondition behavior for a network-bound audit (invalid URL, non-WooCommerce site, minimum requirements), which an agent would want before committing to a 20 s call.

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?

There is a single parameter with 100% schema description coverage, including a format example ('twoj-sklep.pl'), so the baseline is 3. The description adds nothing about the URL semantics — no note on scheme handling, subdirectory installs, or whether a bare domain vs. full path matters.

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 a specific verb and resource ('Pełny audyt strony lub sklepu') and quantifies scope precisely: 68 tests across 8 enumerated categories. The category list (speed, Google/AI assistants, WooCommerce catalog, payment-operator compliance) makes it unmistakable against siblings like pomiar_core_web_vitals or plan_poprawy, which cover only subsets.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

Usage is implied rather than stated — an agent can infer 'call this when the user wants a comprehensive site audit' from the breadth described. However, there is no explicit when-to-use/when-not guidance and no alternative sibling is named (e.g. no direction that a quick performance check should use pomiar_core_web_vitals instead). 'Use for full audit, not for single-metric checks' would have closed the gap.

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