grid-search.versus-3.chatgpt.site WebMCP audit

Name: grid-search.versus-3.chatgpt.site WebMCP audit
Creator: ora

Rescan

audited Sep 4, 2026in 18s

59/ 100100% of the applicable check weight evaluated

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

Shared experience100

Tool selection33

Tool quality84

Trust0

https://grid-search.versus-3.chatgpt.site

Tools

0 read, 0 write, 6 undeclared

Loading map

get_context

Read the concise, static SemanticSpy objective, rules, and tool workflow.No behaviour hints declared. Agents should treat it as possibly state-changing.

pagehttps://grid-search.versus-3.chatgpt.site/

implementation

viaimperative

entry pointdocument

registered after130ms

executepresent

api surfaceTakes no parameters.

annotations

read onlynot declared

untrusted contentnot declared

titlenot declared

1 finding

failAnnotations present

weight 5

2 of 2 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_context, get_state

fix

{
  name: "get_context",
  // 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": "get_context",
  "description": "Read the concise, static SemanticSpy objective, rules, and tool workflow.",
  "inputSchema": {
    "type": "object",
    "properties": {},
    "required": [],
    "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

33 / 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 "I want to submit clue on this site." no tool on the page served it. 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

84 / 100 · weight 25

passRegistration timing

weight 1

Every measured tool registered within 130ms of navigation.

toolmake_guess

passCanonical entry point

weight 3

All 6 tools register on the canonical document.modelContext entry point.

passSchema validity

weight 4

All 6 declared input schemas are structurally valid object schemas.

warningSchema quality

weight 4

5 of 6 tool schemas are harder for an agent to use than they need to be: get_state 1 parameter has no description (playerHandle).

toolget_state

get_state: 1 parameter has no description (playerHandle); submit_clue: 3 parameters have no description (playerHandle, clue, count); make_guess: 2 parameters have no description (playerHandle, word);

fix

{
  name: "get_state",
  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: 3 names do not start with a verb (make_guess).

toolmake_guess

fix

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

passStub detection

weight 4

All 6 tools declare an execute handler.

passRegistration errors

weight 2

No tool registration threw during the capture.

passDescription quality

weight 5

All 6 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

2 of 2 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_context

get_context, get_state

fix

{
  name: "get_context",
  // 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

I want to get context on this site.ok

choseget_contextexpected get contextkind matched

arguments

{}

I want to submit clue on this site.missed

choseno toolexpected submit cluekind not applicable

No tool was picked for this intent.

arguments

{}

I want to make guess on this site.missed

choseno toolexpected make guesskind 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 148.0.7778.96)
chrome: 148.0.7778.96
capture shim: v2
spec snapshot: 2026-08-26
mode: fast
pages: 1 - entry page only
tools: 6
invoked: not invoked; a live audit calls them
run time: 18s
finished: Sep 4, 2026

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