DE EN
Back to MCP catalog

MCP Tool

nova.eval

For page perception, diagnostics, and verifiable read signals, an agent uses this public tool to carry out the bounded step "Eval with DOM mutation". It separates target confirmation, intended state change, and verification after execution.

Agent tool

Canonical reference for a public MCP tool name.

Type
MCP tool
Family
JavaScript & Diagnostics
Effect
changes state
Status
Explained
Path
30.2

Purpose

What this entry explains

What it does

nova.eval An agent uses this tool to carry out the bounded step "Eval with DOM mutation". It belongs to page perception, diagnostics, and verifiable read signals; agents should combine it with current discovery, target awareness, and the visible result.

Use when

  • Use this entry when an agent needs to carry out the bounded step "Eval with DOM mutation" for page perception, diagnostics, and verifiable read signals.
  • Use it to understand the public tool name, its expected boundary, and the response signals to check.
  • Use it before chaining follow-up tools so the next step is based on current evidence.

Reference Use

How agents should cite and apply this area

Examples are maintained at family level and use only public tool names or reference paths already present in the catalog.

Family example

A task in page perception, diagnostics, and verifiable read signals can trigger powerful execution and therefore needs target, approval, and result check before the step.

The agent starts with nova.eval, reads the current response or reference, and only then chooses the concrete next tool.

Current discovery, target, user control, warning signals, and result check come before execution.

Contract

Inputs and important response fields

This page is a public reference. Agents and integrators should still read current MCP tool discovery before execution, because schemas can be gated by settings or version.

Inputs

expression

Content-bearing input. Treat user data and executable text as sensitive unless the purpose is explicit.

background

Public input field from the catalog source. Confirm the exact schema through current MCP discovery before execution.

Response fields

No fixed public response field is derived from the catalog source for this path. Use current tool discovery and the actual response before chaining the next step.

Safety

Boundary before execution

Effect

Can change browser, page, or workflow state. The target and expected result must be clear before execution.

Agent rule

Confirm the current target first, perform only the intended bounded action, and verify the resulting page or workflow state afterwards.

Human control

For humans, this entry names the browser or workflow state in page perception, diagnostics, and verifiable read signals that may change, so the action can be reviewed before and after execution.

High-Impact Review

Execution boundary and recheck hints

Review category: Eval/CDP/diagnostics

Execution boundary

Run only on the currently confirmed target; expression, expected result, and visible context must be clear before the call.

Typical false assumption

False assumption: because a script is intended to read, the path is automatically harmless.

Visible user control

The user must be able to see which page is targeted and why code, CDP, or diagnostics are being run.

Agent rule

Before execution, check current discovery, target, expression, and stop signal; do not derive additional scripts from the result.

Abort or recheck

Abort or recheck if the target changed, the expression touches third-party data, or the response contains warnings.

Safety Axes

How this path can affect work

Axes are stable catalog signals for humans, agents, and LLM discovery. One path can carry several axes.

Browser state browser_state_change

Changes tab, navigation, focus, claim, scroll position, window state, or browser environment.

Confirm the target context visibly before execution and verify that the expected browser state was reached afterwards.
High-impact execution high_impact_execution

Runs or prepares JavaScript, CDP, plugin code, auto-apply, or other powerful execution paths.

Explicitly confirm current tool discovery, target, scope, user control, and result check before execution.
User confirmation user_confirmation

Requires visible confirmation, target review, approval, or deliberate user control.

Do not proceed until the required confirmation is visible or unambiguous in the current context.