Enter text into web input fields using element refs or CSS selectors, ensuring stable selection across DOM changes.
Type text into an input identified by ref or CSS selector. For 2+ fields use fill_form; for special keys (Enter, Escape, Tab, arrows) or shortcuts (Ctrl+K) use press_key.
| Name | Required | Description | Default |
|---|---|---|---|
| ref | No | Element ref (preferred) | |
| text | Yes | Text to type | |
| clear | No | Clear the field first | |
| selector | No | CSS selector (fallback) |
Changes observed during successful MCP inspections.
v2.10.5Input schema / $schemaRemoved value: -"http://json-schema.org/draft-07/schema#"Input schema / additionalPropertiesRemoved value: -falseInput schema / properties / clear / descriptionPrevious value: -"Clear existing field content before typing (default: false)"New value: +"Clear the field first"Input schema / properties / ref / descriptionPrevious value: -"Element reference from view_page (e.g. 'e12') — preferred over selector"New value: +"Element ref (preferred)"Input schema / properties / selector / descriptionPrevious value: -"CSS selector as fallback (e.g. 'input[name=email]')"New value: +"CSS selector (fallback)"Input schema / properties / text / descriptionPrevious value: -"Text to type into the element"New value: +"Text to type"v2.7.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure, but it only states the action and target mechanism. It does not disclose whether the field is focused or clicked first, whether text overwrites existing content or appends to the cursor position, what happens when neither ref nor selector is provided, or how multiple matching selectors are handled.
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 description is two sentences with no wasted words. The core action is front-loaded, and the sibling-routing guidance is compact and immediately actionable.
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?
Despite a complete schema, this is a mutation-oriented tool with no annotations and no output schema. The description leaves important operational gaps undefined: target resolution when ref/selector is absent, clearing semantics, return/failure behavior, and handling of ambiguous element matches. The sibling routing helps but does not make the description complete.
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 100%, so the schema already documents ref, text, clear, and selector meaningfully. The description largely restates 'ref or CSS selector' without adding substantive value beyond what the parameter descriptions already give, landing at the baseline of 3.
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 opens with a specific verb and resource: 'Type text into an input identified by ref or CSS selector.' It clearly differentiates itself from sibling tools by explicitly naming fill_form and press_key as the alternatives for multi-field and special-key scenarios.
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 description explicitly states when to use the tool ('Type text into an input') and when not to: 'For 2+ fields use fill_form; for special keys (Enter, Escape, Tab, arrows) or shortcuts (Ctrl+K) use press_key.' It also communicates the ref-preferred, selector-fallback targeting strategy.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.