dribba.com WebMCP audit

Rescan
audited Aug 28, 2026in 4s
57/ 100

17 tools registered. Strongest in WebMCP use, weakest in human experience.

WebMCP use82
Usefulness50
Human experience6
about:blank

No agent run recorded yet.

No steps recorded

Tools

/
list_services: fail

list_services

List the digital-product services offered by Dribba (end-to-end product studio in Barcelona and Andorra, official Google Flutter Partner in Spain) with a short summary and canonical URL for each.Takes an action on the site.
pagehttps://dribba.com/
implementation
viaimperative
entry pointdocument
registered after322ms
executepresent
api surfaceTakes no parameters.
annotations
read onlynot declared
destructivenot declared
idempotentnot declared
open worldnot declared
untrusted contentnot declared
titlenot declared
2 findings
failAnnotations present
0 / 4
16 of 16 tools declare no readOnlyHint, so an agent cannot tell a read from a write without guessing from the name.
list_services, calculate_app_cost, book_meeting, list_projects, get_case_study
fix
{
  name: "list_services",
  annotations: { readOnlyHint: true, destructiveHint: false, idempotentHint: true }
}
warningHuman parity
0.5 / 8
16 of 17 tools run through the JavaScript API with no visible counterpart, so the person co-browsing cannot see what the agent is offered. Declarative forms (or at least a title annotation) close the gap.
list_services, calculate_app_cost, book_meeting, list_projects, get_case_study
fix
<!-- Give the tool a visible counterpart: a declarative form is one the person can see and use too. -->
<form toolname="list_services" tooldescription="...">
  <!-- the same action, as UI -->
</form>
tool json
{
  "name": "list_services",
  "description": "List the digital-product services offered by Dribba (end-to-end product studio in Barcelona and Andorra, official Google Flutter Partner in Spain) with a short summary and canonical URL for each.",
  "inputSchema": {
    "type": "object",
    "properties": {}
  },
  "annotations": {}
}
Showing list_services

Findings

WebMCP use

82 / 100 · weight 50
passTools registered
4 / 4
16 imperative tools and 1 declarative form registered across 1 page.
passReal-browser eligible
8 / 8
A real browser exposes modelContext natively on this page, so the tools registered here are visible to an agent today.
passRegistration timing
4 / 4
Every measured tool registered within 350.90000009536743ms of navigation. 1 further tool carried no measurable registration time.
toolscheduleMeeting
passCanonical entry point
4 / 4
All 16 tools register on the canonical document.modelContext entry point.
passSchema validity
5 / 5
All 16 tools declare a structurally valid object input schema.
warningSchema quality
3.3 / 4
3 of 17 tool schemas are harder for an agent to use than they need to be: calculate_app_cost 1 parameter description is over Chrome's 150-character guidance.
toolcalculate_app_cost
calculate_app_cost: 1 parameter description is over Chrome's 150-character guidance; request_resource: description is 710 characters, over Chrome's 500-character guidance; openContactForm: declares no
fix
{
  name: "calculate_app_cost",
  inputSchema: {
    type: "object",
    properties: {
      query: { type: "string", description: "What to search for" }
    },
    required: ["query"]
  }
}
passStub detection
5 / 5
All 16 tools declare an execute handler.
failAnnotations present
0 / 4
16 of 16 tools declare no readOnlyHint, so an agent cannot tell a read from a write without guessing from the name.
toollist_services
list_services, calculate_app_cost, book_meeting, list_projects, get_case_study
fix
{
  name: "list_services",
  annotations: { readOnlyHint: true, destructiveHint: false, idempotentHint: true }
}
not applicableAnnotation mismatch
0 / 3
No tool declares a readOnlyHint, so there is no safety claim to contradict.
warningUntrusted content hint
0 / 2
5 of 5 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.
toolsubmit_contact_request
submit_contact_request: message, replie, user; request_resource: user, email; apply_to_job: message, replie, user; openContactForm: message, user; submit_contact_request: user, email
fix
{ name: "submit_contact_request", annotations: { untrustedContentHint: true } }
passRegistration errors
2 / 2
No tool registration threw during the capture.
warningToolchange coherence
1 / 2
16 tools were registered but the page never dispatched a toolchange event, so an agent subscribed to registry updates never learns they exist.
fix
document.modelContext.dispatchEvent(new Event("toolchange"));
not applicableInjection surface
0 / 3
The injection-surface model hop returned no usable result, so tool contracts were not reviewed for injection surface.

Usefulness

50 / 100 · weight 30
warningNaming quality
1 / 2
Tool naming makes selection harder than it needs to be: names mix camel and snake conventions; 3 names do not start with a verb (request_resource).
toolrequest_resource
fix
{ name: "request_resource" /* short, unique, verb-based */ }
not applicableDescription quality
0 / 6
The description-quality model hop returned no usable result, so descriptions were not rated.
not applicableTool selection
0 / 14
The tool-selection model hop returned no usable result.
warningCoverage vs. site type
4 / 8
The tool set covers 2 of the 4 things an agent needs on a saas site; it cannot create a record or start a job or update or move an existing record.

Human experience

6 / 100 · weight 20
warningHuman parity
0.5 / 8
16 of 17 tools run through the JavaScript API with no visible counterpart, so the person co-browsing cannot see what the agent is offered. Declarative forms (or at least a title annotation) close the gap.
toollist_services
list_services, calculate_app_cost, book_meeting, list_projects, get_case_study
fix
<!-- Give the tool a visible counterpart: a declarative form is one the person can see and use too. -->
<form toolname="list_services" tooldescription="...">
  <!-- the same action, as UI -->
</form>
not applicablePage experience
0 / 12
The page-experience model hop returned no usable result, so the page was not graded.

Tool selection

The tool-selection model hop returned no usable result.
how this was captured
chrome
148.0.7778.96
capture shim
v1
spec snapshot
2026-08
mode
fast
pages
1
tools
17
run time
4s
finished
Aug 28, 2026