navigator.berlin WebMCP audit

Name: navigator.berlin WebMCP audit
Creator: ora

Rescan

audited Oct 11, 2026in 12s

91/ 100100% of the applicable check weight evaluated

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

Shared experience100

Tool selection100

Tool quality83

Trust76

https://navigator.berlin

Tools

10 read, 1 write

Loading map

address_lookup

Search Berlin addresses, streets, and POIs. Returns up to N candidates with coordinates and administrative context (Bezirk, Kiez, postcode). Backed by OSM Nominatim, biased to Berlin.Answers a question. Declared read only.

pagehttps://navigator.berlin/

implementation

viaimperative

entry pointdocument

registered after572ms

executepresent

api surface

queryrequired

limitoptional

annotations

read onlytrue

untrusted contentnot declared

titlenot declared

2 findings

warningSchema quality

weight 4

11 of 11 tool schemas are harder for an agent to use than they need to be: address_lookup 2 parameters have no description (query, limit).

address_lookup: 2 parameters have no description (query, limit); cross_layer_query: 2 parameters have no description (lat, lng); list_layers_at_point: 2 parameters have no description (lat, lng); get_

fix

{
  name: "address_lookup",
  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 (address_lookup).

fix

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

tool json

{
  "name": "address_lookup",
  "description": "Search Berlin addresses, streets, and POIs. Returns up to N candidates with coordinates and administrative context (Bezirk, Kiez, postcode). Backed by OSM Nominatim, biased to Berlin.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "query": {
        "type": "string",
        "minLength": 2,
        "maxLength": 120
      },
      "limit": {
        "type": "integer",
        "minimum": 1,
        "maximum": 20
      }
    },
    "required": [
      "query"
    ],
    "additionalProperties": false
  },
  "annotations": {
    "readOnlyHint": 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

83 / 100 · weight 25

passRegistration timing

weight 1

Every measured tool registered within 573ms of navigation.

toolset_finder_weights

passCanonical entry point

weight 3

All 11 tools register on the canonical document.modelContext entry point.

passSchema validity

weight 4

All 11 declared input schemas are structurally valid object schemas.

warningSchema quality

weight 4

11 of 11 tool schemas are harder for an agent to use than they need to be: address_lookup 2 parameters have no description (query, limit).

tooladdress_lookup

address_lookup: 2 parameters have no description (query, limit); cross_layer_query: 2 parameters have no description (lat, lng); list_layers_at_point: 2 parameters have no description (lat, lng); get_

fix

{
  name: "address_lookup",
  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 (address_lookup).

tooladdress_lookup

fix

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

passStub detection

weight 4

All 11 tools declare an execute handler.

passRegistration errors

weight 2

No tool registration threw during the capture.

passDescription quality

weight 5

All 11 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 (11 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

4 of 11 tools carry instruction-shaped text in their own metadata: list_layers_at_point description instructs agent how to use tool.

toollist_layers_at_point

list_layers_at_point: description instructs agent how to use tool; get_layer_metadata: description instructs agent how to use tool; set_finder_weights: description instructs agent to prefer this tool; get_finder_state: description instructs agent when to call tool

fix

{
  name: "list_layers_at_point",
  // 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 address lookup on this site.ok

choseaddress_lookupexpected address lookupkind matched

arguments

{
  "query": "Berlin"
}

I want to cross layer query on this site.ok

chosecross_layer_queryexpected cross layer querykind matched

arguments

{
  "lat": 52.52,
  "lng": 13.4
}

I want to list layers at point on this site.ok

choselist_layers_at_pointexpected list layers at pointkind matched

arguments

{
  "lat": 52.52,
  "lng": 13.4
}

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: 11
invoked: not invoked; a live audit calls them
run time: 12s
finished: Oct 11, 2026

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