prism.alx21.chatgpt.site WebMCP audit

Name: prism.alx21.chatgpt.site WebMCP audit
Creator: ora

Rescan

audited Sep 2, 2026in 21s

98/ 100100% of the applicable check weight evaluated

4 tools registered. Strongest in shared experience, weakest in tool quality.

Shared experience100

Task completion100

Tool quality90

Trust100

https://prism.alx21.chatgpt.site

Tools

2 read, 2 write

Loading map

get_evaluation_context

Read the currently selected WebMCP purpose profile, target label, expected capabilities, and human approval rule shown in Prism.Answers a question. Declared read only.

pagehttps://prism.alx21.chatgpt.site/

implementation

viaimperative

entry pointdocument

registered after850ms

executepresent

api surfaceTakes no parameters.

annotations

read onlytrue

untrusted contentfalse

titlenot declared

0 findingsNo check named this tool.

tool json

{
  "name": "get_evaluation_context",
  "description": "Read the currently selected WebMCP purpose profile, target label, expected capabilities, and human approval rule shown in Prism.",
  "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

100 / 100 · weight 25

passTool selection

weight 15

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.

not applicableCoverage vs. site type

weight 10

This tool set does not place the site in a category with a known expected tool shape, so there is no coverage baseline to score it against.

Tool quality

90 / 100 · weight 25

passRegistration timing

weight 1

Every measured tool registered within 851ms of navigation.

toolchoose_evaluation_profile

passCanonical entry point

weight 3

All 4 tools register on the canonical document.modelContext entry point.

passSchema validity

weight 4

All 4 declared input schemas are structurally valid object schemas.

warningSchema quality

weight 4

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

toolchoose_evaluation_profile

choose_evaluation_profile: 1 parameter has no description (profile); run_sample_evaluation: 1 parameter has no description (profile)

fix

{
  name: "choose_evaluation_profile",
  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: 2 names do not start with a verb (choose_evaluation_profile).

toolchoose_evaluation_profile

fix

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

passStub detection

weight 4

All 4 tools declare an execute handler.

passRegistration errors

weight 2

No tool registration threw during the capture.

passDescription quality

weight 5

All 4 rated tool descriptions say what the tool does, when to use it, and what it returns.

Trust

100 / 100 · weight 20

passAnnotations present

weight 6

All 2 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 6

No tool claims to be read-only while its own name or description says it writes (4 declared hints checked).

not applicableUntrusted content hint

weight 4

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

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

100% across 3 intents

I want to get evaluation context on this site.ok

choseget_evaluation_contextexpected get evaluation contextkind matched

arguments

{}

I want to choose evaluation profile on this site.ok

chosechoose_evaluation_profileexpected choose evaluation profilekind matched

arguments

{
  "profile": "commerce"
}

I want to run sample evaluation on this site.ok

choserun_sample_evaluationexpected run sample evaluationkind matched

arguments

{
  "profile": "commerce"
}

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: 4
run time: 21s
finished: Sep 2, 2026

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