audited Nov 19, 2026in 11s
85/ 100100% of the applicable check weight evaluated

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

Shared experience87
Tool selection100
Tool quality92
Trust57
https://die-partei-reutlingen.de
Captured view of https://die-partei-reutlingen.de

Tools

4 read, 0 write
Loading map
beitraege_suchen: warning

beitraege_suchen

Sucht veröffentlichte Nachrichten, z. B. mit {"thema":"Gemeinderat"}. Nutze url als Quelle und published_at sowie information_status zur zeitlichen Einordnung.Answers a question. Declared read only.

page

https://www.die-partei-reutlingen.de/

implementation

viaimperative
entry pointdocument
registered after150ms
executepresent

api surface

qoptional
jahroptional
themaoptional
seiteoptional

annotations

read onlytrue
untrusted contenttrue
titlenot declared
consequentialfalse

2 findings

warningNaming quality
weight 2
Tool naming makes selection harder than it needs to be: 4 names do not start with a verb (beitraege_suchen).
fix
{ name: "beitraege_suchen" /* short, unique, verb-based */ }
warningInjection surface
weight 3
4 of 4 tools carry instruction-shaped text in their own metadata: beitraege_suchen Description instructs agent how to use tool's output.
beitraege_suchen: Description instructs agent how to use tool's output; termine_suchen: Description instructs agent how to call and use tool; inhalte_suchen: Description instructs agent how to use tool's output and prefer another tool; inhalt_lesen: Description instructs agent how to use tool's output
fix
{
  name: "beitraege_suchen",
  // 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 JSON
{
  "name": "beitraege_suchen",
  "description": "Sucht veröffentlichte Nachrichten, z. B. mit {\"thema\":\"Gemeinderat\"}. Nutze url als Quelle und published_at sowie information_status zur zeitlichen Einordnung.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "q": {
        "type": "string",
        "maxLength": 100,
        "description": "Suchtext; leer oder weggelassen liefert die neuesten Ergebnisse."
      },
      "jahr": {
        "type": "integer",
        "minimum": 2000,
        "maximum": 2100,
        "description": "Veröffentlichungsjahr."
      },
      "thema": {
        "type": "string",
        "maxLength": 100,
        "description": "Exakter öffentlicher Themenname, beispielsweise Gemeinderat."
      },
      "seite": {
        "type": "integer",
        "minimum": 1,
        "maximum": 10000,
        "description": "Ergebnisseite ab 1; zehn Einträge je Seite. Seiten hinter dem Ende liefern eine leere data-Liste."
      }
    },
    "required": [],
    "additionalProperties": false
  },
  "annotations": {
    "readOnlyHint": true,
    "untrustedContentHint": true,
    "consequentialHint": false
  }
}
Showing beitraege_suchen

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 and not consequentialHint: true.
passPage experience
weight 16
1 of 4 page-experience marks came back short: clarity The main content is a large red block with some text, but its purpose is unclear..
clarity: 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 and not consequentialHint: 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

92 / 100 · weight 25
passRegistration timing
weight 1
Every measured tool registered within 151ms of navigation.
toolinhalt_lesen
passCanonical entry point
weight 3
All 4 tools register on the canonical document.modelContext entry point.
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: inhalte_suchen 3 parameters have no description (typ, jahr, page).
toolinhalte_suchen
inhalte_suchen: 3 parameters have no description (typ, jahr, page)
fix
{
  name: "inhalte_suchen",
  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: 4 names do not start with a verb (beitraege_suchen).
toolbeitraege_suchen
fix
{ name: "beitraege_suchen" /* 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.
passDescription quality
weight 5
All 4 rated tool descriptions say what the tool does, when to use it, and what it returns.

Trust

57 / 100 · weight 20
not applicableAnnotations present
weight 4
No tool name reads like a read, and an absent readOnlyHint already defaults to "this may write" - readOnlyHint: true is the hint this check scores, and this set has no read tool to declare it on. (On a write that is significant or hard to undo, consequentialHint: true tells the agent to confirm with the person first.)
passAnnotation mismatch
weight 4
No tool claims to be read-only while its own name or description says it writes (4 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 applicableConsequential hint
weight 3
No tool name reads like a consequential action (a purchase, a booking, a payment, a transfer, a deletion), so there is no consequentialHint to expect.
not applicableHint vs. observed
weight 3
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 and not consequentialHint: true.
warningInjection surface
weight 3
4 of 4 tools carry instruction-shaped text in their own metadata: beitraege_suchen Description instructs agent how to use tool's output.
toolbeitraege_suchen
beitraege_suchen: Description instructs agent how to use tool's output; termine_suchen: Description instructs agent how to call and use tool; inhalte_suchen: Description instructs agent how to use tool's output and prefer another tool; inhalt_lesen: Description instructs agent how to use tool's output
fix
{
  name: "beitraege_suchen",
  // 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 beitraege suchen on this site.ok
chosebeitraege_suchenexpected beitraege suchenkind matched
arguments
{}
I want to termine suchen on this site.ok
chosetermine_suchenexpected termine suchenkind matched
arguments
{}
I want to inhalte suchen on this site.ok
choseinhalte_suchenexpected inhalte suchenkind matched
arguments
{
  "q": ""
}
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.
Reads the site's public pages; takes a few seconds.
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
2026-11-10
mode
fast
pages
1 - entry page only
tools
4
invoked
not invoked; a live audit calls them
run time
11s
finished
Nov 19, 2026
Checked the way in-browser agents discover tools: the top-level document's modelContext registry, read after the page settles.