beenthere.page WebMCP audit

Name: beenthere.page WebMCP audit
Creator: ora

Rescan

audited Sep 5, 2026in 17s

73/ 100100% of the applicable check weight evaluated

35 tools registered. Strongest in trust, weakest in tool selection.

Shared experience87

Tool selection18

Tool quality90

Trust98

https://beenthere.page

Tools

35 read, 0 write

Loading map

list-trips

List all trips for the authenticated user. Returns an array of trips.Answers a question. Declared read only.

pagehttps://www.beenthere.page/

implementation

viaimperative

entry pointdocument

registered after674ms

executepresent

api surfaceTakes no parameters.

annotations

read onlytrue

untrusted contenttrue

titlenot declared

1 finding

warningDescription quality

weight 5

35 of 35 tool descriptions leave an agent guessing: list-trips Omits what comes back, only says it returns an array of trips..

list-trips: weak; get-trip: weak; get-trip-by-slug: weak; get-trip-stamp-eligibility: weak

fix

{
  name: "list-trips",
  description: "Describe what this tool does, when to use it, and what it returns."
}

tool json

{
  "name": "list-trips",
  "description": "List all trips for the authenticated user. Returns an array of trips.",
  "inputSchema": {
    "type": "object",
    "properties": {},
    "required": []
  },
  "annotations": {
    "readOnlyHint": true,
    "untrustedContentHint": 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 page is mostly blank, with only a header and a small icon visible..

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

18 / 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.

failTool selection

weight 12

An agent chose an existing tool and built a schema-valid call that held up on 0 of 3 canonical intents; on "Find a hotel in Lisbon for two nights in June." no tool on the page served it. Nothing was executed, so this verifies selection, not outcomes.

warningCoverage vs. site type

weight 7

The tool set covers 2 of the 4 things an agent needs on a travel site; it cannot book or hold a reservation or look up or change an existing booking.

Tool quality

90 / 100 · weight 25

passRegistration timing

weight 1

Every measured tool registered within 723ms of navigation.

toolget-billing

passCanonical entry point

weight 3

All 35 tools register on the canonical document.modelContext entry point.

passSchema validity

weight 4

All 35 declared input schemas are structurally valid object schemas.

passSchema quality

weight 4

All 24 of 35 tool schemas that declare parameters describe them (the other 11 declare no parameters), and every description stays within Chrome's size guidance.

passNaming quality

weight 2

All 35 tool names are consistent, verb-led, and within Chrome's size guidance.

passStub detection

weight 4

All 35 tools declare an execute handler.

passRegistration errors

weight 2

No tool registration threw during the capture.

warningDescription quality

weight 5

35 of 35 tool descriptions leave an agent guessing: list-trips Omits what comes back, only says it returns an array of trips..

toollist-trips

list-trips: weak; get-trip: weak; get-trip-by-slug: weak; get-trip-stamp-eligibility: weak

fix

{
  name: "list-trips",
  description: "Describe what this tool does, when to use it, and what it returns."
}

Trust

98 / 100 · weight 20

passAnnotations present

weight 5

All 34 read-shaped tools declare readOnlyHint: true - the one declared claim that lets an agent treat a call as safe to make without asking.

warningAnnotation mismatch

weight 5

1 tool declares readOnlyHint: true although the name says the call writes (add-bucket-list-destination).

tooladd-bucket-list-destination

add-bucket-list-destination: readOnlyHint=true

fix

// readOnlyHint must match what the tool actually does - drop it (or set false) on a tool that writes.
{ name: "add-bucket-list-destination", annotations: { readOnlyHint: false } }

passUntrusted content hint

weight 3

All 3 tools that look like they return third-party text declare untrustedContentHint.

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

0% across 3 intents

Find a hotel in Lisbon for two nights in June.missed

choseno toolexpected availability searchkind not applicable

No tool was picked for this intent.

arguments

{}

Show me the details of the cheapest one.missed

choseno toolexpected listing detailkind not applicable

No tool was picked for this intent.

arguments

{}

Look up the status of my existing booking.missed

choseno toolexpected booking lookupkind 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 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: 35
invoked: not invoked; a live audit calls them
run time: 17s
finished: Sep 5, 2026

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