interactive-star-lab.vercel.app WebMCP audit

Name: interactive-star-lab.vercel.app WebMCP audit
Creator: ora

Rescan

audited Sep 5, 2026in 14s

94/ 100100% of the applicable check weight evaluated

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

Shared experience100

Tool selection100

Tool quality97

Trust76

https://interactive-star-lab.vercel.app

Tools

8 read, 13 write

Loading map

get_observation_site

Returns the observation site currently selected in InteractiveStarLab, including its latitude and longitude.Answers a question. Declared read only.

pagehttps://interactive-star-lab.vercel.app/

implementation

viaimperative

entry pointdocument

registered after332ms

executepresent

api surfaceTakes no parameters.

annotations

read onlytrue

untrusted contenttrue

titlenot declared

0 findingsNo check named this tool.

tool json

{
  "name": "get_observation_site",
  "description": "Returns the observation site currently selected in InteractiveStarLab, including its latitude and longitude.",
  "inputSchema": {
    "type": "object",
    "properties": {},
    "additionalProperties": false
  },
  "annotations": {
    "readOnlyHint": true,
    "untrustedContentHint": true
  }
}

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

100 / 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.

passTool selection

weight 12

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 7

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

97 / 100 · weight 25

passRegistration timing

weight 1

Every measured tool registered within 352ms of navigation.

toolgenerate_observation_guide

passCanonical entry point

weight 3

All 21 tools register on the canonical document.modelContext entry point.

passSchema validity

weight 4

All 21 declared input schemas are structurally valid object schemas.

warningSchema quality

weight 4

1 of 21 tool schemas are harder for an agent to use than they need to be: configure_sky_view 3 parameters have no description (azimuth, altitude, fieldOfView).

toolconfigure_sky_view

configure_sky_view: 3 parameters have no description (azimuth, altitude, fieldOfView)

fix

{
  name: "configure_sky_view",
  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: 1 name is over Chrome's 30-character guidance; 6 names do not start with a verb (open_plan_view).

toolcompare_prediction_and_observation

fix

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

passStub detection

weight 4

All 21 tools declare an execute handler.

passRegistration errors

weight 2

No tool registration threw during the capture.

passDescription quality

weight 5

All 21 rated tool descriptions say what the tool does, when to use it, and what it returns.

Trust

76 / 100 · weight 20

passAnnotations present

weight 5

All 8 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 5

No tool claims to be read-only while its own name or description says it writes (21 declared hints checked).

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

10 of 21 tools carry instruction-shaped text in their own metadata: create_observation_plan Description instructs agent to call another tool.

toolcreate_observation_plan

create_observation_plan: Description instructs agent to call another tool; restore_observation_mission: Description instructs agent on conversation and logging; open_sky_view: Description instructs agent to use another tool; set_observation_site: Description provides extraneous information about tool effects

fix

{
  name: "create_observation_plan",
  // 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

100% across 3 intents

I want to get observation site on this site.ok

choseget_observation_siteexpected get observation sitekind matched

arguments

{}

I want to predict visible stars on this site.ok

chosepredict_visible_starsexpected predict visible starskind matched

arguments

{
  "dateTime": "2024-07-20T12:00:00Z",
  "maxMagnitude": 4
}

I want to open plan view on this site.ok

choseopen_plan_viewexpected open plan viewkind 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.

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: 21
invoked: not invoked; a live audit calls them
run time: 14s
finished: Sep 5, 2026

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