specification.website WebMCP audit

Name: specification.website WebMCP audit
Creator: ora

Rescan

audited Sep 6, 2026in 12s

77/ 100100% of the applicable check weight evaluated

5 tools registered. Strongest in shared experience, weakest in tool selection.

Shared experience100

Tool selection33

Tool quality95

Trust76

https://specification.website

Tools

3 read, 2 write

Loading map

search_spec

Search The Website Specification for matching topics. Returns ranked results with title, status, category, canonical URL, and a one-line summary. Use this when the user asks about a topic by keyword (e.g. "CSP", "alt text", "llms.txt").Answers a question. Declared read only.

pagehttps://specification.website/

implementation

viaimperative

entry pointdocument

registered after454ms

executepresent

api surface

queryrequired

limitoptional

annotations

read onlytrue

untrusted contentnot declared

titlenot declared

2 findings

warningSchema quality

weight 4

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

search_spec: 1 parameter has no description (limit)

fix

{
  name: "search_spec",
  inputSchema: {
    type: "object",
    properties: {
      query: { type: "string", description: "What to search for" }
    },
    required: ["query"]
  }
}

warningInjection surface

weight 3

5 of 5 tools carry instruction-shaped text in their own metadata: search_spec Description instructs agent when to use tool.

search_spec: Description instructs agent when to use tool; list_topics: Description instructs agent when to use tool; get_topic: Description instructs agent when to use tool; open_search: Description instructs agent to use another tool

fix

{
  name: "search_spec",
  // 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": "search_spec",
  "description": "Search The Website Specification for matching topics. Returns ranked results with title, status, category, canonical URL, and a one-line summary. Use this when the user asks about a topic by keyword (e.g. \"CSP\", \"alt text\", \"llms.txt\").",
  "inputSchema": {
    "type": "object",
    "properties": {
      "query": {
        "type": "string",
        "description": "Free-text query.",
        "minLength": 1
      },
      "limit": {
        "type": "integer",
        "minimum": 1,
        "maximum": 25,
        "default": 5
      }
    },
    "required": [
      "query"
    ]
  },
  "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

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 search spec on this site." the tool it chose does not look like the kind of tool the intent needs. Nothing was executed, so this verifies selection, not outcomes.

toolopen_search

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

95 / 100 · weight 25

passRegistration timing

weight 1

Every measured tool registered within 455ms of navigation.

toollist_topics

passCanonical entry point

weight 3

All 5 tools register on the canonical document.modelContext entry point.

passSchema validity

weight 4

All 5 declared input schemas are structurally valid object schemas.

warningSchema quality

weight 4

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

toolsearch_spec

search_spec: 1 parameter has no description (limit)

fix

{
  name: "search_spec",
  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 (open_search).

toolopen_search

fix

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

passStub detection

weight 4

All 5 tools declare an execute handler.

passRegistration errors

weight 2

No tool registration threw during the capture.

passDescription quality

weight 5

All 5 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 3 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 (5 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

5 of 5 tools carry instruction-shaped text in their own metadata: search_spec Description instructs agent when to use tool.

toolsearch_spec

search_spec: Description instructs agent when to use tool; list_topics: Description instructs agent when to use tool; get_topic: Description instructs agent when to use tool; open_search: Description instructs agent to use another tool

fix

{
  name: "search_spec",
  // 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

33% across 3 intents

I want to search spec on this site.missed

choseopen_searchexpected search speckind mismatch

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

arguments

{}

I want to list topics on this site.ok

choselist_topicsexpected list topicskind matched

arguments

{}

I want to get topic on this site.missed

choseno toolexpected get topickind 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: 5
invoked: not invoked; a live audit calls them
run time: 12s
finished: Sep 6, 2026

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

Listed in the community directory.