Choose files

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

With no annotations, the description carries the burden and does real work: it explains that a native file chooser is driven, that paths resolve on the host machine (relative to the working folder), and that folder fields accept exactly one folder. It omits whether it waits for the upload to complete, whether the element must be visible, and what failure looks like.

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 sentences, front-loaded with the action, then path semantics. The parenthetical "(or the button or label that opens one)" is slightly awkward but saves an agent from failing on wrapped inputs, so it earns its place.

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 two-parameter tool with no output schema, this covers what an agent needs to call it correctly: the target element, the path base, and the folder case. Only post-action behavior (upload completion, errors) is missing, which is secondary.

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 50% – only `id` is documented there. The description compensates for the bare `files` array by defining path semantics (local, relative to working folder) and the single-item rule for folder fields, which is exactly the missing 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?

"Clicks a file field ... and answers its file chooser with these files" states a concrete verb and resource, and the mechanism (native chooser) makes it distinguishable from the plain click/type siblings. It never names an alternative explicitly, so the differentiation is implied rather than declared.

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?

Usage is implied: this is the tool for file/folder fields rather than ordinary clicking, and the folder-case caveat is given. There is no explicit guidance on when to prefer click, when the field must be visible first, or what to do if no chooser appears.

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