boldreports.com WebMCP audit

Name: boldreports.com WebMCP audit
Creator: ora

Rescan

audited Sep 29, 2026in 13s

57/ 100100% of the applicable check weight evaluated

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

Shared experience100

Tool selection39

Tool quality72

Trust0

https://boldreports.com

Tools

0 read, 0 write, 4 undeclared

Loading map

request-demo

Request a live demo of Bold ReportsNo behaviour hints declared. Agents should treat it as possibly state-changing.

pagehttps://www.boldreports.com/

implementation

viaimperative

entry pointprovideContext

registered after834ms

executepresent

api surface

namerequired

emailrequired

companyoptional

annotations

read onlynot declared

untrusted contentnot declared

titlenot declared

3 findings

failCanonical entry point

weight 3

Every tool uses the removed provideContext API; register each tool with document.modelContext.registerTool().

fix

// document.modelContext is the canonical entry point - the navigator.modelContext alias is deprecated.
document.modelContext.registerTool({ /* ... */ });

warningNaming quality

weight 2

Tool naming makes selection harder than it needs to be: 2 names do not start with a verb (request-demo).

fix

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

warningDescription quality

weight 5

4 of 4 tool descriptions leave an agent guessing: request-demo Omits what comes back, or what changes when it runs..

request-demo: weak; start-free-trial: weak; search-site: weak; contact-sales: weak

fix

{
  name: "request-demo",
  description: "Describe what this tool does, when to use it, and what it returns."
}

tool json

{
  "name": "request-demo",
  "description": "Request a live demo of Bold Reports",
  "inputSchema": {
    "type": "object",
    "properties": {
      "name": {
        "type": "string",
        "description": "Full name"
      },
      "email": {
        "type": "string",
        "description": "Work email address"
      },
      "company": {
        "type": "string",
        "description": "Company name"
      }
    },
    "required": [
      "name",
      "email"
    ]
  },
  "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

39 / 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 1 of 3 canonical intents; on "Show me everything on that record." the tool it chose does not look like the kind of tool the intent needs. Nothing was executed, so this verifies selection, not outcomes.

toolsearch-site

warningCoverage vs. site type

weight 7

The tool set covers 2 of the 4 things an agent needs on a saas site; it cannot read one item in detail or update or move an existing record.

Tool quality

72 / 100 · weight 25

passRegistration timing

weight 1

Every measured tool registered within 834ms of navigation.

toolstart-free-trial

failCanonical entry point

weight 3

Every tool uses the removed provideContext API; register each tool with document.modelContext.registerTool().

toolrequest-demo

fix

// document.modelContext is the canonical entry point - the navigator.modelContext alias is deprecated.
document.modelContext.registerTool({ /* ... */ });

passSchema validity

weight 4

All 4 declared input schemas are structurally valid object schemas.

warningSchema quality

weight 4

1 of 4 tool schemas are harder for an agent to use than they need to be: contact-sales 2 parameters have no description (name, email).

toolcontact-sales

contact-sales: 2 parameters have no description (name, email)

fix

{
  name: "contact-sales",
  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 (request-demo).

toolrequest-demo

fix

{ name: "request-demo" /* 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.

warningDescription quality

weight 5

4 of 4 tool descriptions leave an agent guessing: request-demo Omits what comes back, or what changes when it runs..

toolrequest-demo

request-demo: weak; start-free-trial: weak; search-site: weak; contact-sales: weak

fix

{
  name: "request-demo",
  description: "Describe what this tool does, when to use it, and what it returns."
}

Trust

0 / 100 · weight 20

failAnnotations present

weight 5

1 of 1 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.)

toolsearch-site

search-site

fix

{
  name: "search-site",
  // 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.

not applicableInjection surface

weight 3

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

33% across 3 intents

Find the record for a company called Northwind.ok

chosesearch-siteexpected record searchkind matched

arguments

{
  "query": "Northwind company record"
}

Show me everything on that record.missed

chosesearch-siteexpected record detailkind mismatch

The tool the model chose does not look like the kind of tool this intent needs.

arguments

{
  "query": "Northwind company record details"
}

Create a new contact called Dana Reeve.missed

choseno toolexpected record createkind 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: 13s
finished: Sep 29, 2026

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