artex_browser

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

With no annotations supplied, the description carries the full behavioral burden and only partially meets it. It discloses that sign_in reuses configured Web secrets, which is useful auth context, but says nothing about session persistence, whether the browser is headless, side effects of click/fill/upload, download destinations, or what close does to state.

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

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

The text is short and front-loads what the tool is before drilling into per-action parameter notes. The fragmentary sentence style ('For drag use value as target selector; for tab use its index') is dense but each clause maps to a real parameter, so little is wasted.

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

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

This is a 13-action browser automation surface with five parameters, 0% schema description coverage, no annotations, and no output schema. A four-sentence blurb covering only a handful of actions and four of five parameters leaves an agent without enough to reliably invoke most of the enum values.

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

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

Schema coverage is 0%, so the description must compensate and it does for part of the surface: value means a path on navigate and a target selector on drag, tab takes an index, selector is a Playwright locator, and save_as applies to click downloads. However upload_files is never mentioned and several actions (fill, press, select, hover, screenshot) get no parameter mapping, so the compensation is incomplete.

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

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

The description identifies the tool as an 'Optional Chromium for browser-local UI' and names a couple of operations (navigate, snapshot), so the general domain is clear. But it never enumerates or characterizes the full action set (click, fill, press, select, hover, upload, close, screenshot, tab), leaving an agent to infer most capabilities from the enum.

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

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

There is no guidance on when to reach for this browser tool versus siblings like artex_call or artex_find_routes, and no stated preconditions such as needing an initialized session. The only hints are action-specific mechanics (value for navigate/drag, index for tab, save_as for downloads), which are parameter semantics rather than use guidance.

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