Fill several fields at once in the DESKTOP grid browser (by pageId). One call instead of a web_type per field — noticeably faster on a long form, and it reports which field failed. NOT a device — there is no webpage_fill_form; on a real phone or tablet fill fields one at a time with webpage_type (by udid).
| Name | Required | Description | Default |
|---|---|---|---|
| fields | Yes | Fields to fill, in order | |
| pageId | Yes | Page ID from web_navigate |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the disclosure burden. It usefully explains batch behavior, performance benefit, and that the tool 'reports which field failed.' It could disclose more about partial-fill behavior or permissions, but the core behavioral traits are covered better than most descriptions.
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?
Three sentences with no filler: purpose first, then benefit and failure reporting, then the key device/desktop distinction. Every sentence earns its place, and the structure is easy to scan.
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?
Covers what the tool does, where it applies, when to prefer it, what alternatives exist, and how failures are reported. The only meaningful gap is the inaccurate 'no webpage_fill_form' statement, which could mislead an agent despite an actual sibling tool of that name.
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 baseline is 3. The description adds modest context like 'by pageId' and references to web_type, but the schema already documents pageId as coming from web_navigate and fields as an ordered array of selector/text pairs. It does not materially expand parameter meaning.
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?
Clearly states a specific verb and resource: 'Fill several fields at once in the DESKTOP grid browser (by pageId).' It also distinguishes from web_type. However, it asserts 'there is no webpage_fill_form' while a sibling tool named webpage_fill_form exists in the provided list, so the disambiguation is not fully trustworthy.
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?
Provides explicit usage context: use this for desktop grid browsers, avoid for real phones/tablets, and use webpage_type (by udid) instead for mobile. This is strong guidance, but the claim that webpage_fill_form does not exist conflicts with an actual sibling tool, making the when-not guidance partially unreliable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
