browser_type

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

With no annotations, the description carries the full behavioral burden. It says nothing about whether existing field content is cleared, whether the element is auto-focused, whether typing fires keystroke events, or what happens on failure — all material for an interaction tool. The one behavioral hint it does offer references a flag that isn't in the schema.

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?

Two short sentences, with the core action front-loaded before the modifier. It is tight and earns its length, though the second sentence spends its budget on a flag that does not exist rather than on useful detail.

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?

For a 5-parameter interaction tool with no annotations and no output schema, the description covers almost nothing: no side effects, no prerequisites (e.g. that target refs come from browser_snapshot is only in the schema), no interaction guidance with submit/Enter behavior, and it never resolves the --humanize/slowly discrepancy.

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 description coverage is 80% and the schema already documents target, element, submit, and slowly, so the description need not repeat them. Instead of adding meaning, the description introduces '--humanize', a parameter that does not appear in the schema, which can lead an agent to emit an invalid call.

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?

States a specific verb and resource ('Type text into an editable field'), which is clearly distinct from sibling tools like browser_click or browser_navigate. It stops short of differentiating itself from the closest sibling browser_fill_form (bulk form filling), so it is clear but not fully disambiguated.

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?

The only usage guidance is 'Use --humanize for natural per-character timing', but --humanize does not exist in the input schema; the analogous parameter is 'slowly'. Guidance that points at a nonexistent flag is misleading rather than helpful, and there is no statement of when to prefer this tool over browser_fill_form or browser_press_key.

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