camoufox-agent

browse_session_action

Run one bounded action in an existing browser session to click, fill, type, select, scroll, wait, upload, download, navigate, or evaluate without starting a new session.

Instructions

Run one bounded action in an existing browser session.

Input Schema

Name	Required	Description
`action`	Yes	One bounded action to run in the existing session.
`maxChars`	No	Maximum final visible text characters to return in snapshot.
`selector`	No	Optional CSS selector to limit final snapshot.
`sessionId`	Yes	Session ID returned by browse_session_start.
`maxElements`	No	Maximum final snapshot 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
`action`	Yes
`message`	No
`snapshot`	Yes
`expiresAt`	Yes
`sessionId`	Yes
`challengeType`	No
`captchaIframes`	No
`captchaDetected`	No
`challengeSignals`	No
`challengeHandling`	No
`challengePlaybook`	No
`challengeProvider`	No
`suggestedStrategy`	No
`requiresUserAction`	No
`interactiveElements`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Oct 29, 2026

TDQS

C2.9/5.0

Behavior3/5

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

Annotations already disclose that this is a mutating, open-world, non-idempotent, non-destructive operation. The description adds useful behavioral context by clarifying that exactly one bounded action runs per call and that the session must already exist, but it does not mention side effects of specific actions (e.g., uploads, downloads, waitForHuman, evaluate) or how the action interacts with page state.

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

Conciseness5/5

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

The description is a single front-loaded sentence with zero filler. It is appropriately sized for a tool whose parameter semantics and return shape are fully documented in the schema and output schema.

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

Completeness2/5

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

Given the tool's complexity — six parameters and a large oneOf covering click, fill, upload, download, evaluate, waitForHuman, and more — the description is too thin to orient an agent. Although the schema and output schema are rich, the description does not explain what kind of actions are supported or why an agent would choose this tool over its many siblings, leaving a significant selection gap.

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 schema itself documents every parameter and each action variant in detail. The description adds no parameter-level meaning beyond the schema, so the baseline of 3 is appropriate when structured data carries the full semantic burden.

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 description states a specific verb ('Run') and resource ('one bounded action in an existing browser session'), but 'action' is vague without naming the available action types. It does not distinguish this tool from siblings like browse_session_navigate, browse_sequence, or browse, so an agent cannot confidently choose it over alternatives from the description alone.

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 explicit guidance on when to use this tool versus alternatives. The phrase 'existing browser session' implies it is called after browse_session_start, but it never names browse_session_navigate, browse_sequence, or any other sibling that might be more appropriate for navigation or multi-step flows.

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