ezugc.ai WebMCP audit

Rescan
audited Sep 1, 2026in 15s
98/ 100100% of the applicable check weight evaluated

One declarative form tool registered. Strongest in shared experience, weakest in tool quality. Trust was not measured.

Shared experience100
Task completion100
Tool quality92
TrustN/A
https://ezugc.ai
Captured view of https://ezugc.ai

Tools

0 read, 1 write
Loading map
open_ugc_ad_creator: warning

open_ugc_ad_creator

Open the EzUGC app to start creating a new UGC-style ad. Takes a short ad idea/prompt and the desired creative format, then opens the EzUGC creator in a new tab with those carried as query parameters.Takes an action on the site.Declarative form tool: a Chrome preview whose spec section is still a TODO in the pinned draft. The capture finds it by scanning the markup and cannot observe a browser registering it, so it is listed but not scored.
pagehttps://www.ezugc.ai/
implementation
viadeclarative
entry pointform
registered afternot measured
executepresent
api surfaceTakes no parameters.
annotations
read onlynot declared
untrusted contentnot declared
titlenot declared
1 finding
warningNaming quality
weight 2
Tool naming makes selection harder than it needs to be: 1 name does not start with a verb (open_ugc_ad_creator).
fix
{ name: "open_ugc_ad_creator" /* short, unique, verb-based */ }
tool json
{
  "name": "open_ugc_ad_creator",
  "description": "Open the EzUGC app to start creating a new UGC-style ad. Takes a short ad idea/prompt and the desired creative format, then opens the EzUGC creator in a new tab with those carried as query parameters.",
  "inputSchema": null,
  "annotations": {}
}
Showing open_ugc_ad_creator

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, and 1 declarative form doubles as visible counterparts.

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 1 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

92 / 100 · weight 25
not applicableRegistration timing
weight 1
No tool is registered through the JavaScript API, so there is no registration moment to time.
not applicableCanonical entry point
weight 3
No tool is registered through the JavaScript API, so there is no entry point to score.
not applicableSchema validity
weight 4
Declarative form tools carry their inputs as form fields rather than a JSON Schema, so there is no schema to validate.
passSchema quality
weight 4
1 tool declares no parameters, and every description stays within Chrome's size guidance.
warningNaming quality
weight 2
Tool naming makes selection harder than it needs to be: 1 name does not start with a verb (open_ugc_ad_creator).
toolopen_ugc_ad_creator
fix
{ name: "open_ugc_ad_creator" /* short, unique, verb-based */ }
not applicableStub detection
weight 4
Every tool on this page is a declarative form, which the browser submits itself, so there is no execute handler to check.
passRegistration errors
weight 2
No tool registration threw during the capture.
passDescription quality
weight 5
All 1 rated tool descriptions say what the tool does, when to use it, and what it returns.

Trust

not measured
not applicableAnnotations present
weight 6
Declarative form tools have nowhere to declare behaviour hints, so there are no annotations to score.
not applicableAnnotation mismatch
weight 6
No tool declares a readOnlyHint, so there is no safety claim to contradict.
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 1 intents
I want to open ugc ad creator on this site.ok
choseopen_ugc_ad_creatorexpected open ugc ad creatorkind matched
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.
Reads the site's public pages; takes a few seconds.
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
native modelContext
chrome
148.0.7778.96
capture shim
v1
spec snapshot
2026-08-26
mode
fast
pages
1 - entry page only
tools
1
run time
15s
finished
Sep 1, 2026
Checked the way in-browser agents discover tools: the top-level document's modelContext registry, read after the page settles.