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

With no annotations provided, the description carries the full burden and does so impressively. It discloses that the tool bypasses the file picker, fires input/change events, reads back what the page actually sees (names and sizes), and enforces a 2 MB content limit. This gives the agent a complete picture of side effects and failure-detection mechanisms without needing external hints.

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 a single, dense paragraph that front-loads the primary purpose and then adds critical constraints and behaviors. Every sentence earns its place: the file-picker avoidance, the 'only way' rationale, the content-source options, and the event-firing/verification details. No redundancy or irrelevant filler.

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?

Given a 5-parameter tool with no output schema, the description is remarkably complete. It covers invocation options (selector, index, pageId), file-source choices (text, base64, devicePath), the 2 MB cap, and what the tool returns conceptually (file names and sizes the page sees). The only missing piece is the exact response format, but the description's statement suffices for an agent to understand what to expect.

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 100%, so the baseline is 3. The description adds meaningful operational context beyond the schema: how to supply file content (inline vs. devicePath), the total 2 MB limit, and the verification behavior that helps the agent interpret results. It also implicitly guides the choice between text, contentBase64, and devicePath by mentioning 'file content inline, or name a file already on the device'.

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 clearly identifies the action ('Set the files') and the resource ('file-upload input in Safari on an iOS device'), and it explicitly distinguishes the tool from siblings by noting it works WITHOUT opening the device's file picker. It also differentiates from file-related tools like ios_file_push/ios_upload_targets by focusing on the input element, not the device filesystem.

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 this tool—'This is the only way to test an upload flow end to end on iOS'—and explains why (tapping an upload control opens a native sheet automation cannot drive). It also references complementary tools (ios_file_push / ios_upload_targets) for getting files onto the device, giving clear alternatives for that aspect. The 'only way' phrasing also implies when not to use other approaches.

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