Name: sema.run WebMCP audit
Creator: ora

Tools

/

read_editor

Read Sema source from the playground editor. Use this before editing or running unfamiliar code.Answers a question. Declared read only.

pagehttps://sema.run/

implementation

viaimperative

entry pointdocument

registered after503ms

executepresent

api surface

offsetoptional

limitoptional

annotations

read onlytrue

destructivenot declared

idempotentnot declared

open worldnot declared

untrusted contenttrue

titlenot declared

2 findings

warningSchema quality

3.1 / 4

4 of 17 tool schemas are harder for an agent to use than they need to be: read_editor declares no required list, so an agent cannot tell which parameters are mandatory.

read_editor: declares no required list, so an agent cannot tell which parameters are mandatory; read_output: declares no required list, so an agent cannot tell which parameters are mandatory; find_exa

fix

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

warningHuman parity

0 / 8

17 of 17 tools run through the JavaScript API with no visible counterpart, so the person co-browsing cannot see what the agent is offered. Declarative forms (or at least a title annotation) close the gap.

read_editor, write_editor, format_editor, run_editor, stop_run

fix

<!-- Give the tool a visible counterpart: a declarative form is one the person can see and use too. -->
<form toolname="read_editor" tooldescription="...">
  <!-- the same action, as UI -->
</form>

tool json

{
  "name": "read_editor",
  "description": "Read Sema source from the playground editor. Use this before editing or running unfamiliar code.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "offset": {
        "type": "integer",
        "minimum": 0,
        "default": 0,
        "description": "Zero-based character offset at which to start reading."
      },
      "limit": {
        "type": "integer",
        "minimum": 1,
        "maximum": 12000,
        "default": 1500,
        "description": "Maximum number of characters to return."
      }
    },
    "additionalProperties": false
  },
  "annotations": {
    "readOnlyHint": true,
    "untrustedContentHint": true
  }
}

Findings

WebMCP use

96 / 100 · weight 50

passTools registered

4 / 4

17 tools registered across 1 page.

passReal-browser eligible

8 / 8

A real browser exposes modelContext natively on this page, so the tools registered here are visible to an agent today.

passRegistration timing

4 / 4

Every measured tool registered within 503.0750000476837ms of navigation.

toolget_debug_state

passCanonical entry point

4 / 4

All 17 tools register on the canonical document.modelContext entry point.

passSchema validity

5 / 5

All 17 tools declare a structurally valid object input schema.

warningSchema quality

3.1 / 4

4 of 17 tool schemas are harder for an agent to use than they need to be: read_editor declares no required list, so an agent cannot tell which parameters are mandatory.

toolread_editor

read_editor: declares no required list, so an agent cannot tell which parameters are mandatory; read_output: declares no required list, so an agent cannot tell which parameters are mandatory; find_exa

fix

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

passStub detection

5 / 5

All 17 tools declare an execute handler.

passAnnotations present

4 / 4

All 17 tools declare a readOnlyHint, so an agent knows which calls change state.

passAnnotation mismatch

3 / 3

No tool claims to be read-only while its name says it writes (17 declared hints checked).

not applicableUntrusted content hint

0 / 2

No tool's contract suggests it returns text written by somebody other than the site, so there is nothing to flag as untrusted.

passRegistration errors

2 / 2

No tool registration threw during the capture.

warningToolchange coherence

1 / 2

17 tools were registered but the page never dispatched a toolchange event, so an agent subscribed to registry updates never learns they exist.

fix

document.modelContext.dispatchEvent(new Event("toolchange"));

not applicableInjection surface

0 / 3

The injection-surface model hop returned no usable result, so tool contracts were not reviewed for injection surface.

Usefulness

79 / 100 · weight 30

warningNaming quality

1.6 / 2

Tool naming makes selection harder than it needs to be: 7 names do not start with a verb (format_editor).

toolformat_editor

fix

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

not applicableDescription quality

0 / 6

The description-quality model hop returned no usable result, so descriptions were not rated.

not applicableTool selection

0 / 14

The tool-selection model hop returned no usable result.

not applicableCoverage vs. site type

0 / 8

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.

Human experience

0 / 100 · weight 20

warningHuman parity

0 / 8

17 of 17 tools run through the JavaScript API with no visible counterpart, so the person co-browsing cannot see what the agent is offered. Declarative forms (or at least a title annotation) close the gap.

toolread_editor

read_editor, write_editor, format_editor, run_editor, stop_run

fix

<!-- Give the tool a visible counterpart: a declarative form is one the person can see and use too. -->
<form toolname="read_editor" tooldescription="...">
  <!-- the same action, as UI -->
</form>

not applicablePage experience

0 / 12

The page-experience model hop returned no usable result, so the page was not graded.

Tool selection

The tool-selection model hop returned no usable result.

how this was captured

chrome: 148.0.7778.96
capture shim: v1
spec snapshot: 2026-08
mode: fast
pages: 1
tools: 17
run time: 5s
finished: Aug 28, 2026