camoufox-agent

browse_session_snapshot

Read-only

Capture the current visible text and ARIA snapshot of an existing browser session to inspect page state, limit extraction by CSS selector, and control CAPTCHA handling.

Instructions

Read the current state of an existing browser session.

Input Schema

Name	Required	Description
`maxChars`	No	Maximum visible text and ARIA snapshot characters to return.
`selector`	No	Optional CSS selector to limit snapshot extraction.
`sessionId`	Yes	Session ID returned by browse_session_start.
`maxElements`	No	Maximum interactive elements to return.
`captchaPolicy`	No	Challenge handling policy. 'detect' reports signals, 'pause' returns state for human action, 'fail' returns an error, 'attempt' returns enhanced challenge metadata, interactive elements, a bounded screenshot, and a suggested strategy. When CAPTCHA_AUTONOMOUS=true, responses are marked for LLM-assisted handling and include provider-specific challengePlaybook context when known.

Output Schema

Name	Required	Description	Default
`url`	Yes
`text`	Yes
`title`	No
`status`	No
`message`	No
`elements`	Yes
`maxChars`	Yes
`selector`	No
`expiresAt`	Yes
`sessionId`	Yes
`contentType`	No
`diagnostics`	No
`maxElements`	Yes
`ariaSnapshot`	No
`challengeType`	No
`selectorFound`	Yes
`textTruncated`	Yes
`captchaIframes`	No
`captchaDetected`	No
`challengeSignals`	No
`ariaSnapshotError`	No
`challengeHandling`	No
`challengePlaybook`	No
`challengeProvider`	No
`elementsTruncated`	Yes
`suggestedStrategy`	No
`requiresUserAction`	No
`interactiveElements`	No
`ariaSnapshotTruncated`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Oct 29, 2026

TDQS

C2.7/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, so safety is covered. The description adds nothing beyond that - it doesn't say what a snapshot contains, whether it reflects live page state, or how the captchaPolicy affects the response, all of which are non-obvious for a page-state read.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with zero filler. It is efficient, though the terseness is achieved by omitting useful content rather than by tight writing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists and the input schema is fully self-documenting, so return-value and parameter detail needn't be repeated. What is missing is the relational context: how this snapshot relates to browse_snapshot and when a session-scoped read is the right call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the CAPTCHA policy enum is fully documented inline, so the schema carries the parameter burden. The description adds no parameter meaning on top of it, which lands at the baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The verb and resource are clear ('read state of an existing browser session'), which is more specific than a tautology. However, with siblings like browse_snapshot, browse_inspect, and browse_outline in the same family, the description gives no signal about how a session snapshot differs from a plain snapshot.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this versus browse_snapshot or browse_inspect, and no prerequisites are stated (e.g. that a session must first be started via browse_session_start). The agent must infer everything from the sessionId parameter name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.