deploy-preview-10148--atlan-com.netlify.app WebMCP audit

Name: deploy-preview-10148--atlan-com.netlify.app WebMCP audit
Creator: ora

Rescan

audited Sep 1, 2026in 13s

65/ 100100% of the applicable check weight evaluated

7 tools registered. Strongest in shared experience, weakest in task completion.

Shared experience100

Task completion20

Tool quality96

Trust30

https://deploy-preview-10148--atlan-com.netlify.app

Tools

0 read, 2 write, 5 undeclared

Loading map

what_is_atlan

Explain what Atlan is and does: the Context Layer for AI, the Enterprise Data Graph, who uses it, and where to learn more. No input. Returns a short plain-text explanation with canonical URLs.No behaviour hints declared. Agents should treat it as possibly state-changing.

pagehttps://deploy-preview-10148--atlan-com.netlify.app/

implementation

viaimperative

entry pointdocument

registered after641ms

executepresent

api surfaceTakes no parameters.

annotations

read onlynot declared

untrusted contentnot declared

titlenot declared

2 findings

warningNaming quality

weight 2

Tool naming makes selection harder than it needs to be: 3 names do not start with a verb (what_is_atlan).

fix

{ name: "what_is_atlan" /* short, unique, verb-based */ }

warningInjection surface

weight 4

6 of 7 tools carry instruction-shaped text in their own metadata: what_is_atlan Description instructs on output format.

what_is_atlan: Description instructs on output format; list_atlan_products: Description instructs on output format; list_customer_stories: Description instructs on output format; get_atlan_resources: Description instructs on output format

fix

{
  name: "what_is_atlan",
  // Metadata DESCRIBES the tool - it never addresses the agent reading it.
  // Rewrite any name, description, title, or schema field description that
  // instructs the agent (which tool to prefer, what to output, rules to
  // ignore) so it states what the tool does and what it returns instead.
  description: "Searches the catalog and returns matching items with prices."
}

tool json

{
  "name": "what_is_atlan",
  "description": "Explain what Atlan is and does: the Context Layer for AI, the Enterprise Data Graph, who uses it, and where to learn more. No input. Returns a short plain-text explanation with canonical URLs.",
  "inputSchema": {
    "type": "object",
    "properties": {},
    "additionalProperties": false
  },
  "annotations": {}
}

Findings

Shared experience

100 / 100 · weight 30

passPage experience

weight 20

The page a person sees holds up next to the agent surface: a working interface, visible actions, readable content, nothing in the way.

passHuman parity

weight 10

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

Task completion

20 / 100 · weight 25

failTool selection

weight 15

An agent chose an existing tool and built a schema-valid call that held up on 0 of 3 canonical intents; on "Find a carry-on suitcase under 300 dollars." no tool on the page served it. Nothing was executed, so this verifies selection, not outcomes.

warningCoverage vs. site type

weight 10

The tool set covers 2 of the 4 things an agent needs on a commerce site; it cannot add to or read the cart or start checkout or place an order.

Tool quality

96 / 100 · weight 25

passRegistration timing

weight 1

Every measured tool registered within 641ms of navigation.

toolfill_lead_form

passCanonical entry point

weight 3

All 7 tools register on the canonical document.modelContext entry point.

passSchema validity

weight 4

All 7 declared input schemas are structurally valid object schemas.

warningSchema quality

weight 4

1 of 7 tool schemas are harder for an agent to use than they need to be: list_customer_stories declares no required list, so an agent cannot tell which parameters are mandatory.

toollist_customer_stories

list_customer_stories: declares no required list, so an agent cannot tell which parameters are mandatory

fix

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

warningNaming quality

weight 2

Tool naming makes selection harder than it needs to be: 3 names do not start with a verb (what_is_atlan).

toolwhat_is_atlan

fix

{ name: "what_is_atlan" /* short, unique, verb-based */ }

passStub detection

weight 4

All 7 tools declare an execute handler.

passRegistration errors

weight 2

No tool registration threw during the capture.

passDescription quality

weight 5

All 7 rated tool descriptions say what the tool does, when to use it, and what it returns.

Trust

30 / 100 · weight 20

failAnnotations present

weight 6

3 of 3 read-shaped tools do not declare readOnlyHint: true, so an agent has to treat them as possible writes and ask before calling. (Declaring readOnlyHint: false earns nothing - it is the default.)

toollist_atlan_products

list_atlan_products, list_customer_stories, get_atlan_resources

fix

{
  name: "list_atlan_products",
  // Declare readOnlyHint: true on tools that truly have no side effects -
  // that is the claim that lets an agent relax confirmation on reads.
  // (false is the default, so declaring it adds no information.)
  annotations: { readOnlyHint: true }
}

passAnnotation mismatch

weight 6

No tool claims to be read-only while its own name or description says it writes (2 declared hints checked).

warningUntrusted content hint

weight 4

1 of 1 tools look like they return text written by other people but declare no untrustedContentHint, so an agent will treat the response as the site speaking.

toolfill_lead_form

fill_lead_form: user, email

fix

{ name: "fill_lead_form", annotations: { untrustedContentHint: true } }

warningInjection surface

weight 4

6 of 7 tools carry instruction-shaped text in their own metadata: what_is_atlan Description instructs on output format.

toolwhat_is_atlan

what_is_atlan: Description instructs on output format; list_atlan_products: Description instructs on output format; list_customer_stories: Description instructs on output format; get_atlan_resources: Description instructs on output format

fix

{
  name: "what_is_atlan",
  // Metadata DESCRIBES the tool - it never addresses the agent reading it.
  // Rewrite any name, description, title, or schema field description that
  // instructs the agent (which tool to prefer, what to output, rules to
  // ignore) so it states what the tool does and what it returns instead.
  description: "Searches the catalog and returns matching items with prices."
}

Tool selection

0% across 3 intents

Find a carry-on suitcase under 300 dollars.missed

choseno toolexpected product searchkind not applicable

No tool was picked for this intent.

arguments

{}

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

choseno toolexpected product detailkind not applicable

No tool was picked for this intent.

arguments

{}

Add two of them to my cart.missed

choseno toolexpected cart writekind not applicable

No tool was picked for this intent.

arguments

{}

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 148.0.7778.96)
chrome: 148.0.7778.96
capture shim: v1
spec snapshot: 2026-08-26
mode: fast
pages: 1 - entry page only
tools: 7
run time: 13s
finished: Sep 1, 2026

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