yassinechabli.com WebMCP audit

Name: yassinechabli.com WebMCP audit
Creator: ora

Rescan

audited Sep 13, 2026in 12s

59/ 100100% of the applicable check weight evaluated

4 tools registered. Strongest in shared experience, weakest in trust.

Shared experience100

Tool selection18

Tool quality99

Trust0

https://yassinechabli.com

Tools

0 read, 0 write, 4 undeclared

Loading map

get_page_markdown

Lit la representation Markdown de la page courante de yassinechabli.com, frontmatter compris (titre, description, URL canonique, date de mise a jour). A utiliser avant de citer un contenu de cette page.No behaviour hints declared. Agents should treat it as possibly state-changing.

pagehttps://yassinechabli.com/

implementation

viaimperative

entry pointdocument

registered after178ms

executepresent

api surfaceTakes no parameters.

annotations

read onlynot declared

untrusted contentnot declared

titlenot declared

2 findings

failAnnotations present

weight 5

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.)

get_page_markdown, list_training_offers, list_bootcamp_sessions

fix

{
  name: "get_page_markdown",
  // 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 }
}

warningInjection surface

weight 3

3 of 4 tools carry instruction-shaped text in their own metadata: get_page_markdown description instructs agent when to use tool.

get_page_markdown: description instructs agent when to use tool; list_training_offers: description instructs agent what questions to answer; list_bootcamp_sessions: description instructs agent when to use tool

fix

{
  name: "get_page_markdown",
  // 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": "get_page_markdown",
  "description": "Lit la representation Markdown de la page courante de yassinechabli.com, frontmatter compris (titre, description, URL canonique, date de mise a jour). A utiliser avant de citer un contenu de cette page.",
  "inputSchema": {
    "type": "object",
    "properties": {},
    "additionalProperties": false
  },
  "annotations": {}
}

Findings

Shared experience

100 / 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

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 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 search trips or inventory or book or hold a reservation.

Tool quality

99 / 100 · weight 25

passRegistration timing

weight 1

Every measured tool registered within 178ms of navigation.

toolopen_coaching_booking

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.

passSchema quality

weight 4

4 tools declare 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_coaching_booking).

toolopen_coaching_booking

fix

{ name: "open_coaching_booking" /* 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

0 / 100 · weight 20

failAnnotations present

weight 5

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.)

toolget_page_markdown

get_page_markdown, list_training_offers, list_bootcamp_sessions

fix

{
  name: "get_page_markdown",
  // 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 }
}

not applicableAnnotation mismatch

weight 5

No tool declares a readOnlyHint, so there is no safety claim to contradict.

not applicableUntrusted content hint

weight 3

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

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.

warningInjection surface

weight 3

3 of 4 tools carry instruction-shaped text in their own metadata: get_page_markdown description instructs agent when to use tool.

toolget_page_markdown

get_page_markdown: description instructs agent when to use tool; list_training_offers: description instructs agent what questions to answer; list_bootcamp_sessions: description instructs agent when to use tool

fix

{
  name: "get_page_markdown",
  // 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 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: 4
invoked: not invoked; a live audit calls them
run time: 12s
finished: Sep 13, 2026

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