nightstand-diary.vercel.app WebMCP audit

Name: nightstand-diary.vercel.app WebMCP audit
Creator: ora

Rescan

audited Sep 6, 2026in 12s

92/ 100100% of the applicable check weight evaluated

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

Shared experience100

Tool selection100

Tool quality91

Trust70

https://nightstand-diary.vercel.app

Tools

5 read, 14 write

Loading map

log_entries

Log one or more entries in the person's health diary. Accepts several at once: if someone mentions a symptom and a medication in the same sentence, log them in a single call rather than calling this tool twice. Only records what the person said — it does not interpret, diagnose or suggest dosages.Takes an action on the site.

pagehttps://nightstand-diary.vercel.app/

implementation

viaimperative

entry pointdocument

registered after176ms

executepresent

api surface

entriesrequired

annotations

read onlyfalse

untrusted contentnot declared

titlenot declared

3 findings

warningSchema quality

weight 4

8 of 19 tool schemas are harder for an agent to use than they need to be: log_entries 1 parameter has no description (entries).

log_entries: 1 parameter has no description (entries); edit_entry: 1 parameter has no description (payload); delete_entry: 1 parameter has no description (id); add_medication: 2 parameters have no des

fix

{
  name: "log_entries",
  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: 7 names do not start with a verb (log_entries).

fix

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

warningInjection surface

weight 3

6 of 19 tools carry instruction-shaped text in their own metadata: log_entries Description instructs agent how to use tool, and what not to do.

log_entries: Description instructs agent how to use tool, and what not to do; get_today: Description instructs agent what not to do; add_medication: Description instructs agent what not to do; get_summary: Description instructs agent what not to do

fix

{
  name: "log_entries",
  // 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": "log_entries",
  "description": "Log one or more entries in the person's health diary. Accepts several at once: if someone mentions a symptom and a medication in the same sentence, log them in a single call rather than calling this tool twice. Only records what the person said — it does not interpret, diagnose or suggest dosages.",
  "inputSchema": {
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "type": "object",
    "properties": {
      "entries": {
        "minItems": 1,
        "maxItems": 20,
        "type": "array",
        "items": {
          "oneOf": [
            {
              "type": "object",
              "properties": {
                "kind": {
                  "type": "string",
                  "const": "symptom"
                },
                "name": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 80
                },
                "severity": {
                  "type": "integer",
                  "minimum": 0,
                  "maximum": 10
                },
                "location": {
                  "type": "string",
                  "maxLength": 80
                }
              },
              "required": [
                "kind",
                "name",
                "severity"
              ],
              "additionalProperties": false
            },
            {
              "type": "object",
              "properties": {
                "kind": {
                  "type": "string",
                  "const": "dose"
                },
                "medId": {
                  "type": "string",
                  "minLength": 1
                },
                "name": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 80
                },
                "amount": {
                  "type": "string",
                  "maxLength": 40
                }
              },
              "required": [
                "kind",
                "name",
                "amount"
              ],
              "additionalProperties": false
            },
            {
              "type": "object",
              "properties": {
                "kind": {
                  "type": "string",
                  "const": "sleep"
                },
                "hours": {
                  "type": "number",
                  "minimum": 0,
                  "maximum": 24
                },
                "quality": {
                  "type": "integer",
                  "minimum": 0,
                  "maximum": 10
                }
              },
              "required": [
                "kind",
                "hours",
                "quality"
              ],
              "additionalProperties": false
            },
            {
              "type": "object",
              "properties": {
                "kind": {
                  "type": "string",
                  "const": "note"
                },
                "text": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 1000
                }
              },
              "required": [
                "kind",
                "text"
              ],
              "additionalProperties": false
            }
          ]
        }
      }
    },
    "required": [
      "entries"
    ],
    "additionalProperties": false
  },
  "annotations": {
    "readOnlyHint": false
  }
}

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

91 / 100 · weight 25

passRegistration timing

weight 1

Every measured tool registered within 177ms of navigation.

toolset_accessibility

passCanonical entry point

weight 3

All 19 tools register on the canonical document.modelContext entry point.

passSchema validity

weight 4

All 19 declared input schemas are structurally valid object schemas.

warningSchema quality

weight 4

8 of 19 tool schemas are harder for an agent to use than they need to be: log_entries 1 parameter has no description (entries).

toollog_entries

log_entries: 1 parameter has no description (entries); edit_entry: 1 parameter has no description (payload); delete_entry: 1 parameter has no description (id); add_medication: 2 parameters have no des

fix

{
  name: "log_entries",
  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: 7 names do not start with a verb (log_entries).

toollog_entries

fix

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

passStub detection

weight 4

All 19 tools declare an execute handler.

passRegistration errors

weight 2

No tool registration threw during the capture.

passDescription quality

weight 5

All 19 rated tool descriptions say what the tool does, when to use it, and what it returns.

Trust

70 / 100 · weight 20

warningAnnotations present

weight 5

1 of 6 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.)

toolexport_vault

export_vault

fix

{
  name: "export_vault",
  // 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 }
}

passAnnotation mismatch

weight 5

No tool claims to be read-only while its own name or description says it writes (19 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

6 of 19 tools carry instruction-shaped text in their own metadata: log_entries Description instructs agent how to use tool, and what not to do.

toollog_entries

log_entries: Description instructs agent how to use tool, and what not to do; get_today: Description instructs agent what not to do; add_medication: Description instructs agent what not to do; get_summary: Description instructs agent what not to do

fix

{
  name: "log_entries",
  // 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 log entries on this site.ok

choselog_entriesexpected log entrieskind matched

arguments

{
  "entries": [
    {
      "kind": "symptom",
      "name": "",
      "severity": 0
    }
  ]
}

I want to get today on this site.ok

choseget_todayexpected get todaykind matched

arguments

{}

I want to list entries on this site.ok

choselist_entriesexpected list entrieskind 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: native modelContext
chrome: 151.0.7922.34
capture shim: v3
spec snapshot: 2026-08-26
mode: fast
pages: 1 - entry page only
tools: 19
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.