frictionglass-parity-lab.alx21.chatgpt.site WebMCP audit

Name: frictionglass-parity-lab.alx21.chatgpt.site WebMCP audit
Creator: ora

Rescan

audited Sep 1, 2026in 14s

72/ 100100% of the applicable check weight evaluated

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

Shared experience100

Task completion13

Tool quality91

Trust78

https://frictionglass-parity-lab.alx21.chatgpt.site

Tools

4 read, 6 write

Loading map

get_test_scenario

Read the active FrictionGlass event-registration scenario, expected outcome, visible prices, conditions, and parity dimensions. Read-only.Answers a question. Declared read only.

pagehttps://frictionglass-parity-lab.alx21.chatgpt.site/

implementation

viaimperative

entry pointdocument

registered after432ms

executepresent

api surfaceTakes no parameters.

annotations

read onlytrue

untrusted contentfalse

titlenot declared

0 findingsNo check named this tool.

tool json

{
  "name": "get_test_scenario",
  "description": "Read the active FrictionGlass event-registration scenario, expected outcome, visible prices, conditions, and parity dimensions. Read-only.",
  "inputSchema": {
    "type": "object",
    "properties": {},
    "additionalProperties": false
  },
  "annotations": {
    "readOnlyHint": true,
    "untrustedContentHint": false
  }
}

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

13 / 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 "Open the document I was working on most recently." no tool on the page served it. Nothing was executed, so this verifies selection, not outcomes.

failCoverage vs. site type

weight 10

The tool set covers 1 of the 3 things an agent needs on a editor site; it cannot edit or write content or save, publish, or share the result.

Tool quality

91 / 100 · weight 25

passRegistration timing

weight 1

Every measured tool registered within 432ms of navigation.

toolpropose_interface_patch

passCanonical entry point

weight 3

All 10 tools register on the canonical document.modelContext entry point.

passSchema validity

weight 4

All 10 declared input schemas are structurally valid object schemas.

warningSchema quality

weight 4

4 of 10 tool schemas are harder for an agent to use than they need to be: start_agent_run 1 parameter has no description (reset).

toolstart_agent_run

start_agent_run: 1 parameter has no description (reset); configure_registration: 2 parameters have no description (ticket, seat_preference); submit_parity_finding: 4 parameters have no description (di

fix

{
  name: "start_agent_run",
  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: 4 names do not start with a verb (inspect_task_state).

toolinspect_task_state

fix

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

passStub detection

weight 4

All 10 tools declare an execute handler.

passRegistration errors

weight 2

No tool registration threw during the capture.

passDescription quality

weight 5

1 of 10 tool descriptions leave an agent guessing: complete_simulated_task Does not specify what is returned or what changes beyond 'Mutating'..

toolcomplete_simulated_task

complete_simulated_task: weak

Trust

78 / 100 · weight 20

warningAnnotations present

weight 6

1 of 4 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.)

toolreview_registration

review_registration

fix

{
  name: "review_registration",
  // 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 (10 declared hints checked).

warningUntrusted content hint

weight 4

1 of 2 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.

toolreview_registration

review_registration: review, issue

fix

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

not applicableInjection surface

weight 4

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

Open the document I was working on most recently.missed

choseno toolexpected document openkind not applicable

No tool was picked for this intent.

arguments

{}

Add a short summary paragraph at the top.missed

choseno toolexpected content editkind not applicable

No tool was picked for this intent.

arguments

{}

Save it and give me a link I can share.missed

choseno toolexpected save or sharekind 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: v2
spec snapshot: 2026-08-26
mode: fast
pages: 1 - entry page only
tools: 10
run time: 14s
finished: Sep 1, 2026

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