spree.apparel.monster WebMCP audit

Name: spree.apparel.monster WebMCP audit
Creator: ora

Rescan

audited Sep 6, 2026in 14s

91/ 100100% of the applicable check weight evaluated

16 tools registered. Strongest in tool selection, weakest in tool quality.

Shared experience87

Tool selection100

Tool quality81

Trust100

https://spree.apparel.monster

Tools

10 read, 6 write

Loading map

search_products

Search for apparel products by name, category (taxon permalink), price range, or stock status. Returns up to 20 results with name, price, and URL.Answers a question. Declared read only.

pagehttps://apparel.monster/

implementation

viaimperative

entry pointnavigator

registered after1034ms

executepresent

api surface

queryoptional

taxonoptional

min_priceoptional

max_priceoptional

in_stockoptional

sortoptional

limitoptional

annotations

read onlytrue

untrusted contentnot declared

titlenot declared

2 findings

warningCanonical entry point

weight 3

8 of 16 tools use the removed provideContext API instead of document.modelContext.registerTool().

fix

// document.modelContext is the canonical entry point - the navigator.modelContext alias is deprecated.
document.modelContext.registerTool({ /* ... */ });

warningSchema quality

weight 4

3 of 16 tool schemas are harder for an agent to use than they need to be: search_products 1 parameter has no description (limit).

search_products: 1 parameter has no description (limit); add_to_cart: 1 parameter has no description (quantity); apply_coupon: 1 parameter has no description (coupon_code); search_products: 1 paramete

fix

{
  name: "search_products",
  inputSchema: {
    type: "object",
    properties: {
      query: { type: "string", description: "What to search for" }
    },
    required: ["query"]
  }
}

tool json

{
  "name": "search_products",
  "description": "Search for apparel products by name, category (taxon permalink), price range, or stock status. Returns up to 20 results with name, price, and URL.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "query": {
        "type": "string",
        "description": "Keyword to match against product names, e.g. 'denim shirt'."
      },
      "taxon": {
        "type": "string",
        "description": "Permalink filter, e.g. 'categories/men/shirts' or 'collections/new-arrivals'."
      },
      "min_price": {
        "type": "number",
        "minimum": 0,
        "description": "Minimum price in USD."
      },
      "max_price": {
        "type": "number",
        "minimum": 0,
        "description": "Maximum price in USD."
      },
      "in_stock": {
        "type": "boolean",
        "description": "If true, only return purchasable items in stock.",
        "default": true
      },
      "sort": {
        "type": "string",
        "enum": [
          "popularity",
          "-popularity",
          "price",
          "-price",
          "name",
          "-name",
          "-available_on"
        ],
        "description": "Sort order.",
        "default": "-popularity"
      },
      "limit": {
        "type": "integer",
        "minimum": 1,
        "maximum": 20,
        "default": 10
      }
    }
  },
  "annotations": {
    "readOnlyHint": true
  }
}

Findings

Shared experience

87 / 100 · weight 30

not applicableVisible effect

weight 6

Not invoked on this run: this audit did not call any tool. Scheduled re-audits only read the registry; a live audit from the report page calls the tools that declare readOnlyHint: true.

passPage experience

weight 16

1 of 4 page-experience marks came back short: clarity The main content area shows placeholders, making it unclear what is being offered..

clarity: weak

passHuman parity

weight 8

The person co-browsing can see and use this page - the same page the agent's tools act on.

Tool selection

100 / 100 · weight 25

not applicableInvoke success rate

weight 6

Not invoked on this run: this audit did not call any tool. Scheduled re-audits only read the registry; a live audit from the report page calls the tools that declare readOnlyHint: true.

passTool selection

weight 12

An agent chose an existing, callable tool and built a schema-valid call for all 3 canonical intents, each matching the kind of tool its intent needs. Nothing was executed, so this verifies selection, not outcomes.

passCoverage vs. site type

weight 7

The tool set covers the whole core commerce flow: search or browse the catalog, read one item in detail, add to or read the cart, start checkout or place an order.

Tool quality

81 / 100 · weight 25

warningRegistration timing

weight 1

The slowest tool took 1035ms to register, past the 1000ms an agent reading the registry at first paint would wait for.

tooladd_to_cart

add_to_cart: registered at 1035ms

fix

// Register tools as soon as they're ready, not behind a deferred/async chunk.
document.modelContext.registerTool({ /* ... */ });

warningCanonical entry point

weight 3

8 of 16 tools use the removed provideContext API instead of document.modelContext.registerTool().

toolsearch_products

fix

// document.modelContext is the canonical entry point - the navigator.modelContext alias is deprecated.
document.modelContext.registerTool({ /* ... */ });

passSchema validity

weight 4

All 16 declared input schemas are structurally valid object schemas.

warningSchema quality

weight 4

3 of 16 tool schemas are harder for an agent to use than they need to be: search_products 1 parameter has no description (limit).

toolsearch_products

search_products: 1 parameter has no description (limit); add_to_cart: 1 parameter has no description (quantity); apply_coupon: 1 parameter has no description (coupon_code); search_products: 1 paramete

fix

{
  name: "search_products",
  inputSchema: {
    type: "object",
    properties: {
      query: { type: "string", description: "What to search for" }
    },
    required: ["query"]
  }
}

passNaming quality

weight 2

All 16 tool names are consistent, verb-led, and within Chrome's size guidance.

passStub detection

weight 4

All 16 tools declare an execute handler.

failRegistration errors

weight 2

8 tool registrations threw during the capture, so the registry an agent reads is incomplete.

duplicate tool name registered: search_products

fix

document.modelContext.registerTool({ /* ... */ }).catch(function (err) {
  console.error("WebMCP registration failed", err);
});

passDescription quality

weight 5

All 8 rated tool descriptions say what the tool does, when to use it, and what it returns. 8 of 16 tools were not rated and are excluded from this score.

Trust

100 / 100 · weight 20

passAnnotations present

weight 5

All 10 read-shaped tools declare readOnlyHint: true - the one declared claim that lets an agent treat a call as safe to make without asking.

passAnnotation mismatch

weight 5

No tool claims to be read-only while its own name or description says it writes (16 declared hints checked).

not applicableUntrusted content hint

weight 3

No tool's contract suggests it returns text written by somebody other than the site, so there is nothing to flag as untrusted.

not applicableHint vs. observed

weight 4

Not invoked on this run: this audit did not call any tool. Scheduled re-audits only read the registry; a live audit from the report page calls the tools that declare readOnlyHint: true.

not applicableInjection surface

weight 3

No tool's metadata carries instruction-shaped text aimed at the agent reading it. This check only ever flags; it never credits a site.

Tool selection

100% across 3 intents

Find a carry-on suitcase under 300 dollars.ok

chosesearch_productsexpected product searchkind matched

arguments

{
  "query": "carry-on suitcase",
  "max_price": 300
}

Show me the details and price of the first result.ok

choseget_productexpected product detailkind matched

arguments

{
  "slug": "carry-on-suitcase"
}

Add two of them to my cart.ok

choseadd_to_cartexpected cart writekind matched

arguments

{
  "variant_id": 12345,
  "quantity": 2
}

model: gemini-2.5-flash

Add the tools this site is missing

Our scanner reads your website and suggests the right WebMCP tools for it.

The open source webmcp plugin teaches your coding agent to audit a site, implement tools on document.modelContext, and verify them in a real browser. npx @ora-ai/webmcp-verify runs the verification on its own. No signup, no hosted service.

how this was captured

observed via: capture shim (Chromium 151.0.7922.34)
chrome: 151.0.7922.34
capture shim: v3
spec snapshot: 2026-08-26
mode: fast
pages: 1 - entry page only
tools: 16
invoked: not invoked; a live audit calls them
run time: 14s
finished: Sep 6, 2026

Checked the way in-browser agents discover tools: the top-level document's modelContext registry, read after the page settles.

Listed in the community directory.