homemoneyfinder.com WebMCP audit

Name: homemoneyfinder.com WebMCP audit
Creator: ora

Rescan

audited Sep 9, 2026in 14s

72/ 100100% of the applicable check weight evaluated

4 tools registered. Strongest in tool selection, weakest in trust.

Shared experience87

Tool selection100

Tool quality86

Trust0

https://homemoneyfinder.com

Tools

0 read, 0 write, 4 undeclared

Loading map

find_homebuyer_options

Run the Texas Homebuyer Money Finder assessment and return POSSIBLE Texas homebuyer-assistance program matches (grants, down-payment assistance, closing-cost help). Returns possible matches only — never a qualification, eligibility, or approval decision. No credit pull or SSN is used.No behaviour hints declared. Agents should treat it as possibly state-changing.

pagehttps://homemoneyfinder.com/

implementation

viaimperative

entry pointdocument

registered after609ms

executepresent

api surface

cityoptional

countyoptional

householdSizeoptional

incomeRangeoptional

firstTimeBuyeroptional

needDownPaymentoptional

veteranStatusoptional

occupationoptional

ruralOpenoptional

creditRangeoptional

priceRangeoptional

completedEducationoptional

annotations

read onlynot declared

untrusted contentnot declared

titlenot declared

2 findings

warningCanonical entry point

weight 3

2 of 4 tools use the removed provideContext API instead of document.modelContext.registerTool().

fix

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

failAnnotations present

weight 5

4 of 4 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.)

find_homebuyer_options, get_valid_inputs, find_homebuyer_options, get_valid_inputs

fix

{
  name: "find_homebuyer_options",
  // 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 }
}

tool json

{
  "name": "find_homebuyer_options",
  "description": "Run the Texas Homebuyer Money Finder assessment and return POSSIBLE Texas homebuyer-assistance program matches (grants, down-payment assistance, closing-cost help). Returns possible matches only — never a qualification, eligibility, or approval decision. No credit pull or SSN is used.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "city": {
        "type": "string",
        "description": "City where the buyer intends to purchase."
      },
      "county": {
        "type": "string",
        "description": "County where the buyer intends to purchase."
      },
      "householdSize": {
        "type": "integer",
        "description": "Number of people in the household.",
        "minimum": 1
      },
      "incomeRange": {
        "type": "string",
        "enum": [
          "under_40k",
          "40k_60k",
          "60k_80k",
          "80k_100k",
          "100k_120k",
          "120k_140k",
          "over_140k"
        ],
        "description": "Approximate annual household income range."
      },
      "firstTimeBuyer": {
        "type": "string",
        "enum": [
          "yes",
          "no",
          "not_sure"
        ],
        "description": "Whether the buyer has owned a home in the last 3 years."
      },
      "needDownPayment": {
        "type": "string",
        "enum": [
          "down_payment",
          "closing_costs",
          "both",
          "not_sure"
        ],
        "description": "Type of assistance the buyer is seeking."
      },
      "veteranStatus": {
        "type": "string",
        "enum": [
          "none",
          "veteran",
          "active_duty",
          "national_guard",
          "surviving_spouse"
        ],
        "description": "Military service status, if any."
      },
      "occupation": {
        "type": "string",
        "enum": [
          "none",
          "teacher",
          "nurse",
          "first_responder",
          "corrections",
          "other_public",
          "other"
        ],
        "description": "Profession-based pathway factor, if any."
      },
      "ruralOpen": {
        "type": "string",
        "enum": [
          "yes",
          "no",
          "maybe"
        ],
        "description": "Whether the buyer is open to a rural or small-town property."
      },
      "creditRange": {
        "type": "string",
        "enum": [
          "below_580",
          "580_619",
          "620_639",
          "640_679",
          "680_plus"
        ],
        "description": "Self-estimated credit score range (no credit is pulled)."
      },
      "priceRange": {
        "type": "string",
        "enum": [
          "under_200k",
          "200k_300k",
          "300k_400k",
          "400k_500k",
          "over_500k"
        ],
        "description": "Target purchase price range."
      },
      "completedEducation": {
        "type": "string",
        "enum": [
          "yes",
          "no",
          "started"
        ],
        "description": "Homebuyer education status."
      }
    },
    "required": [],
    "additionalProperties": false
  },
  "annotations": {}
}

Findings

Shared experience

87 / 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

1 of 4 page-experience marks came back short: readability The text is difficult to read due to low contrast with the background..

readability: weak

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 2 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

86 / 100 · weight 25

passRegistration timing

weight 1

Every measured tool registered within 610ms of navigation.

toolget_valid_inputs

warningCanonical entry point

weight 3

2 of 4 tools use the removed provideContext API instead of document.modelContext.registerTool().

toolfind_homebuyer_options

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.

passSchema quality

weight 4

All 2 of 4 tool schemas that declare parameters describe them (the other 2 declare no parameters), and every description stays within Chrome's size guidance.

passNaming quality

weight 2

All 4 tool names are consistent, verb-led, and within Chrome's size guidance.

passStub detection

weight 4

All 4 tools declare an execute handler.

failRegistration errors

weight 2

2 tool registrations threw during the capture, so the registry an agent reads is incomplete.

duplicate tool name registered: find_homebuyer_options

fix

document.modelContext.registerTool({ /* ... */ }).catch(function (err) {
  console.error("WebMCP registration failed", err);
});

passDescription quality

weight 5

All 2 rated tool descriptions say what the tool does, when to use it, and what it returns. 2 of 4 tools were not rated and are excluded from this score.

Trust

0 / 100 · weight 20

failAnnotations present

weight 5

4 of 4 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.)

toolfind_homebuyer_options

find_homebuyer_options, get_valid_inputs, find_homebuyer_options, get_valid_inputs

fix

{
  name: "find_homebuyer_options",
  // 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

100% across 2 intents

I want to find homebuyer options on this site.ok

chosefind_homebuyer_optionsexpected find homebuyer optionskind matched

arguments

{
  "city": "Austin",
  "county": "Travis",
  "householdSize": 2,
  "incomeRange": "80k_100k",
  "firstTimeBuyer": "yes",
  "needDownPayment": "both",
  "veteranStatus": "no"
}

I want to get valid inputs on this site.ok

choseget_valid_inputsexpected get valid inputskind 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: 4
invoked: not invoked; a live audit calls them
run time: 14s
finished: Sep 9, 2026

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