browser_upload_file

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

With no annotations, the description carries the full behavioral burden and does so richly: it explains the bridge reads from disk, streams in ~384 KB chunks, constructs real File objects, fires input + change on an <input type=file>, and falls back to dragenter/dragover/drop on a bare drop zone. It also discloses the tab-affinity constraint for large uploads, which is a real operational gotcha.

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?

Front-loaded with purpose, then mechanism, then a well-organized Args block and a return-shape line. Every element is load-bearing given the 0% schema coverage, though the multi-line prose is on the longer side for a single tool.

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?

No annotations and no output schema exist, and the description fills both gaps: it covers mutation behavior, event side effects, chunking, tab pinning, and the exact return payload ({ok, mode, files, chunks, bytes, transport, seconds}). An agent has everything needed to call this correctly.

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 0%, so the description must compensate, and it documents all four parameters: path (absolute, or list for multi-file), selector (input, containing element, or drop zone), mode (with its three literal values spelled out since no enum exists in the schema), and tab_id (default active, plus why to pin it). This adds meaning the schema cannot supply.

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 ('Attach local file(s) to a page's upload control') and immediately differentiates itself from OS-level file dialogs. No sibling tool (browser_drag, browser_form_fill, browser_fill) overlaps with this behavior, so the scope is unambiguous.

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?

Gives clear operational context: omit selector to hit the first input[type=file], use mode 'auto'/'input'/'drop' depending on the target, and pass tab_id for anything large. It does not name when-not-to-use or an alternative tool, but no plausible sibling alternative exists for file attachment, so the missing exclusion is low-cost.

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